This repo collects the latest fashion-related papers on top AI conferences (in 🔥Latest section).
- If your work relates to this topic and you'd like to be added to this repo, feel free to open an issue ✨.
Change Log
-
2026-6, SIGGRAPH/ECCV 2026 fashion-related papers are updated.
-
2026-5, Fashion-related papers in CVPR/SIGGRAPH 2026 are updated.
-
2026-2, Fashion-related papers in ICLR 2026 are updated.
-
2025-10, Fashion-related papers in SIGGRAPH Asia/NeurIPS 2025 are updated.
-
2025-07, Fashion-related papers in ICCV 2025 are updated.
-
2025-06, Fashion-centric metrics are involved, Fashion-related papers in SIGGRAPH 2025 are updated.
-
2025-03, Fashion-related papers in CVPR/ICLR 2025 are updated.
-
2025-02, 'GenAI in Fashion: Overview' is accepted by ACM TIST(JCR Q1).
This is also the official repo of Generative AI in Fashion: Overview (ACM TIST 2025) ⬅️

Labels: 🏅best / 🏆oral / 🌟highlight.
ECCV 2026-Fashion-Related-Papers
| No | Title | Authors | Key words |
|---|---|---|---|
| 1 | Re-CatVTON: Rethinking Garment Conditioning in Diffusion-based Virtual Try-On | Kihyun Na, Jinyoung Choi, Injung Kim | virtual try-on, garment conditioning, diffusion models |
| 2 | FitControler: Toward Fit-Aware Virtual Try-On | Lu Yang, Yicheng Liu, Yanan Li, Xiang Bai, Hao Lu | virtual try-on, fit-aware control, garment fit |
| 3 | Self-supervised Garment Dynamics with Persistent Wrinkles | Xiaoyuan Yang, Deshan Gong, Taku Komura, He Wang | garment dynamics, persistent wrinkles, cloth simulation |
| 4 | OrthoTryOn: Geometric Orthogonalization for Conflict-Free Unified Fashion Generation | Authors not listed yet | fashion generation, virtual try-on, garment reconstruction |
SIGGRAPH 2026-Fashion-Related-Papers
| No | Title | Authors | Key words |
|---|---|---|---|
| 1 | ControlTile: Controllable Texture Tiling with Transformed RoPE-Enhanced Diffusion Models | Junrong HUANG · Zhiyuan ZHANG · Tang RUI · Hongbo FU · Jing LIAO* | texture, textile, pattern design |
| 2 | Efficient B-Spline Finite Elements for Cloth Simulation | Yuqi Meng, Yihao Shi, Kemeng Huang, Zixuan Lu, Ning Guo, Taku Komura, Yin Yang, Minchen Li | cloth, simulation, finite elements |
| 3 | HairPort: 3D-aware Hairstyle Transfer | A. Heidari, A. Alimohammadi, W. Michel Pinto Lira, A. Bar-Lev, and A. Mahdavi-Amiri | hairstyle, 3D reconstruction, diffusion models |
| 4 | Garment Particles: A 2D-3D Symmetric Garment Representation for Generation and Editing | Kiyohiro Nakayama, I-chao Shen, Ruofan Liu, Yiming Wang, Gordon Wetzstein, Takeo Igarashi | garment generation, garment editing, 2D-3D representation |
| 5 | LoBoFit: Flexible Garment Refitting via Local Bone Mapping Blending | Meng Zhang, Yu Xin, Feiya Guo, Kaizhang Kang, Mengyu Chu, Ruizhen Hu | garment refitting, local bone mapping |
| 6 | Learning Sewing Patterns via Latent Flow Matching of Implicit Fields | Cong Cao, Ren Li, Corentin Dumery, Hao Li | sewing pattern, latent flow matching, implicit fields |
| 7 | PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments | Zhenyang Li, Lutao Jiang, Yizhou Zhao, Weikai Chen, Ying-Cong Chen, Xin Wang, Yifan Peng | garment, sewing pattern, simulation-ready |
| 8 | Learned Universal Interoperable Virtual Try-ON | Cong Cao, Xianhang Cheng, Jingyuan Liu, Yujian Zheng, Zhenhui Lin, Ren Li, Meriem Chkir, Hao Li | virtual try-on, garment interoperability, geometry |
| 9 | FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On | Yuanhao Wang, Johanna Karras, Yingwei Li, Ira Kemelmacher-Shlizerman | virtual try-on, dataset, fit-aware |
| 10 | FabricTryOn: Taming Image Editing Models for Garment Re-Texturing | Jun Ma, Qian He, Gaofeng He, Huang Chen, Chen Liu, Xiaogang Jin, Yin Yang, Huamin Wang | virtual try-on, garment re-texturing, image editing |
| 11 | HumanFlow: Controllable Human Image Generation via Flow Matching | Wenzhuo Fan, Hongsheng Zheng, Jianchi Sun, Fei Fang, Hong Ding, Chunxia Xiao | human image generation, flow matching, virtual try-on |
CVPR 2026-Fashion-Related-Papers
| No | Title | Authors | Key words |
|---|---|---|---|
| 1 | GraspALL: Adaptive Structural Compensation from Luminance Variation for Robotic Garment Grasping in Any Low-Light Conditions 🌟highlight | Haifeng Zhong, Wenshuo Han, Zhouyu Wang, Runyang Feng, Fan Tang, Tong-yee Lee, zipei fan, Ruihai Wu, Yuran Wang, Hao Dong, Hechang Chen, Hyung Jin Chang, Yixing Gao | garment |
| 2 | NI-Tex: Non-isometric Image-based Garment Texture Generation 🌟highlight | Hui Shan, Ming Li, Haitao Yang, Kai Zheng, Sizhe Zheng, Yanwei Fu, Xiangru Huang | garment |
| 3 | SwiftTailor: Efficient 3D Garment Generation with Geometry Image Representation 🌟highlight | Phuc Pham, Uy Tran, Binh-Son Hua, Phong Nguyen | garment |
| 4 | Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and Accessories | Junyao Hu, Zhongwei Cheng, Waikeung Wong, Xingxing Zou | garment, cloth, try-on |
| 5 | ReWeaver: Towards Simulation-Ready and Topology-Accurate Garment Reconstruction | Ming Li, Hui Shan, Kai Zheng, Chentao Shen, Siyu Liu, Yanwei Fu, Zhen Chen, Xiangru Huang | garment, clothed human |
| 6 | FEAT: Fashion Editing and Try-On from Any Design 🌟highlight | Soye Kwon, Keonyoung Lee, Dahuin Jung, Jaekoo Lee | fashion, try-on |
| 7 | MOFA-VTON: More Fashion Possibilities with Fine-Grained Adaptations in Virtual Try-On 🌟highlight | Xiaoyu Han, Chenyang Wang, Jing Wang, Shunyuan Zheng, Quanling Meng, Shengping Zhang | fashion, try-on |
| 8 | MV-Fashion: Towards Enabling Virtual Try-On and Size Estimation with Multi-View Paired Data 🌟highlight | Hunor Laczko, Libang Jia, Phat Truong, Diego Hernández, Sergio Escalera, Jordi Gonzàlez, Meysam Madadi | fashion, try-on |
| 9 | Clothe and Pose | Nakul Sharma, Aayush Bansal, Minh Vo | cloth |
| 10 | Physical Adversarial Clothing Evades Visible-Thermal Detectors via Non-Overlapping RGB-T Pattern | Xiaopei Zhu, Guanning Zeng, Zhanhao Hu, Jun Zhu, Xiaolin Hu | cloth |
| 11 | BarbieGait: An Identity-Consistent Synthetic Human Dataset with Versatile Cloth-Changing for Gait Recognition | Qingyuan Cai, Saihui Hou, Xuecai Hu, Yongzhen Huang | cloth, clothed human |
| 12 | Zero-Shot Reconstruction of Animatable 3D Avatars with Cloth Dynamics from a Single Image | Joohyun Kwon, Geonhee Sim, Gyeongsik Moon | cloth, clothed human |
| 13 | RefTON: Person-to-Person Virtual Try-On with Unpaired Visual References | Liuzhuozheng Li, Yue Gong, Shanyuan Liu, Zanyi Wang, Dengyang Jiang, Liebucha Wu, Bo Cheng, Yuhang Ma, Dawei Leng, Yuhui Yin | clothed human, try-on |
| 14 | Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision 🌟highlight | Hyunsoo Cha, Wonjung Woo, Byungjun Kim, Hanbyul Joo | clothed human, try-on |
| 15 | High-Fidelity Virtual Try-On beyond Paired Data Scarcity via Diffusion-based Cycle-Consistent Learning | Jia Wu, Yijing Dai, Tingfeng Cao, Meiling Wu, Tao Luo, Jian Dong Zhang, Guangming Lu, Xiaoyi Zeng | try-on |
| 16 | Mobile-VTON: High-Fidelity On-Device Virtual Try-On | Zhenchen Wan, Ce Chen, Runqi Lin, Jiaxin Huang, Tianxi Chen, Yanwu Xu, Tongliang Liu, Mingming Gong | try-on |
| 17 | PG-VTON: Single-Pass Training-Free Virtual Try-On via Patch-Guided Reference Alignment | Guohao Zhao, Yuxin Peng | try-on |
| 18 | PROMO: Promptable Outfitting for Efficient High-Fidelity Virtual Try-On | Haohua Chen, Tianze Zhou, Wei Zhu, Runqi Wang, Yandong Guan, Dejia Song, Yibo Chen, Xu Tang, Yao Hu, Lu Sheng, Zhiyong Wu | try-on |
| 19 | The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injection | Qingdong He, Xueqin Chen, Yanjie Pan, Peng Tang, Pengcheng Xu, Zhenye Gan, Chengjie Wang, Xiaobin Hu, Jiangning Zhang, Yabiao Wang | try-on |
| 20 | AvatarMix: Identity-Preserving Cross-Avatar Composition for Outfit Personalization | Zhaorong Wang, Yoshihiro Kanamori, Yuki Endo | outfit personalization, clothed avatar, garment transfer |
| 21 | One Model for All: Unified Try-On and Try-Off in Any Pose via LLM-Inspired Bidirectional Tweedie Diffusion | Jinxi Liu, Zijian He, Guangrun Wang, Guanbin Li, Liang Lin | virtual try-on, try-off, diffusion models |
| 22 | Eevee: Towards Close-up High-resolution Video-based Virtual Try-on | Jianhao Zeng, Yancheng Bai, Ruidong Chen, Xuanpu Zhang, Lei Sun, Dongyang Jin, Ryan Xu, Nannan Zhang, Dan Song, Xiangxiang Chu | video virtual try-on, garment consistency, dataset |
| 23 | Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition | Yu He, Ting Zhu, Yichun Liu, Lichen Ma, Xinyuan Shan, Jingling Fu, Yu Shi, Junshi Huang, Yan Li | fashion dataset, outfit generation, multimodal condition |
| 24 | FIRE-CIR: Fine-grained Reasoning for Composed Fashion Image Retrieval | François Gardères, Camille-Sovanneary Gauthier, Jean Ponce, Shizhe Chen | fashion retrieval, composed image retrieval, reasoning |
| 25 | Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems | Jiahuan Long, Tingsong Jiang, Hanqing Liu, Chao Ma, Weien Zhou, Yang Yang, Wen Yao | clothing, adversarial wearable, dual-modal camouflage |
ICLR 2026-Fashion-Related-Papers
| No | Title | Authors | Key words |
|---|---|---|---|
| 1 | GarmentGPT: Compositional Garment Pattern Generation via Discrete Latent Tokenization | Fangsheng Weng, Junhao Chen, Xiang Li, Jie Qin, Hanzhong Guo, ShaochunHao, Xiaoguang Han | Garment, Pattern |
| 2 | Anime-Ready: Controllable 3D Anime Character Generation with Body-Aligned Component-Wise Garment Modeling | Jiachen Qian, Hongye Yang, Youtian Lin, tianhao zhao, Hengshuang Zhao, Yao Yao, Feihu Zhang | Garment |
| 3 | Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals | Davide Lobba, Fulvio Sanguigni, Bin Ren, Marcella Cornia, Rita Cucchiara, Nicu Sebe | Virtual Try-Off, Fashion, Generation, Diffusion Transformer |
| 4 | Dynamic Texture Modeling of 3D Clothed Gaussian Avatars from a Single Video | Seungeun Lee, SeungJun Moon, Hah Min Lew, Ji-Su Kang, Gyeong-Moon Park | Clothed Human |
| 5 | UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections | Zeyu Cai, Ziyang Li, Xiaoben Li, Boqian Li, Zeyu Wang, Zhenyu Zhang, Yuliang Xiu | Clothed Human |
| 6 | Generative Human Geometry Distribution | Xiangjun Tang, Biao Zhang, Peter Wonka | Clothed Human |
| 7 | CloDS: Visual-Only Unsupervised Cloth Dynamics Learning in Unknown Conditions | Yuliang Zhan, Jian Li, Wenbing Huang, Wenbing Huang, Yang Liu, Hao Sun | Cloth Dynamics, Simulation |
NeurIPS 2025-Fashion-Related-Papers
| No | Title | Authors | Key words |
|---|---|---|---|
| 1 | Mitigating Occlusions in Virtual Try-On via A Simple-Yet-Effective Mask-Free Framework | Chenghu Du · Shengwu Xiong · junyin Wang · Yi Rong · Shili Xiong | try-on |
| 2 | ShoeFit: A New Dataset and Dual-image-stream DiT Framework for Virtual Footwear Try-On | Yuhan Li · Zhiyu Jin · Yifan Tong · Wenxiang Shang · Benlei Cui · Xuanhong Chen · Ran Lin · Bingbing Ni | try-on |
| 3 | VTON-VLLM: Aligning Virtual Try-On Models with Human Preferences | Siqi Wan · Jingwen Chen · Qi Cai · Yingwei Pan · Ting Yao · Tao Mei | try-on |
| 4 | PhysDiff-VTON: Cross-Domain Physics Modeling and Trajectory Optimization for Virtual Try-On | Shibin Mei · Bingbing Ni | try-on |
| 5 | OmniTry: Virtual Try-On Anything without Masks | Yutong Feng · Linlin Zhang · Hengyuan Cao · Yiming Chen · Xiaoduan Feng · Jian Cao · Yuxiong Wu · Bin Wang | try-on |
| 6 | Virtual Fitting Room: Generating Arbitrarily Long Videos of Virtual Try-On from a Single Image | Junkun Chen · Aayush Bansal · Minh Vo · Yu-Xiong Wang | try-on |
| 7 | SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction | Wenyue Chen, Peng Li, Wangguandong Zheng, Chengfeng Zhao, Mengfei Li, Yaolong Zhu, Zhiyang Dou, Ronggang Wang, Yuan Liu | clothed-human |
SIGGRAPH Asia 2025-Fashion-Related-Papers
| No | Title | Authors | Key words |
|---|---|---|---|
| 1 | GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling | Siran Li, Chen Liu, Ruiyang Liu, Zhendong Wang, Gaofeng He, Yong-Lu Li, Xiaogang Jin, Huamin Wang | sewing |
| 2 | DreamO: A Unified Framework for Image Customization | Chong Mou, Yanze Wu, Wenxu Wu, Zinan Guo, Pengze Zhang, Yufeng Cheng, Yiming Luo, Fei Ding, Shiwen Zhang, Xinghui Li, Mengtian Li, Mingcong Liu, Yi Zhang, Shaojin Wu, Songtao Zhao, Jian Zhang, Qian He, Xinglong Wu | try-on |
| 3 | One-shot Embroidery Customization via Contrastive LoRA Modulation | Jun Ma, Qian He, Gaofeng He, Huang Chen, Chen Liu, Xiaogang Jin, Huamin Wang | stylization, embroidery |
| 4 | InfiniHuman: Infinite 3D Human Creation with Precise Control | Yuxuan Xue, Xianghui Xie, Margaret Kostyrko, Gerard Pons-Moll | try-on, clothed human |
| 5 | CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modeling | Yuze He, Yanning Zhou, Wang Zhao, Jingwen Ye, Yushi Bai, Kaiwen Xiao, Yong-Jin Liu, Zhongqian Sun, Wei Yang | hairstyle |
ICCV 2025-Fashion-Related-Papers
| No | Title | Authors | Key words |
|---|---|---|---|
| 1 | CSD-VAR: Content-Style Decomposition in Visual Autoregressive Models | Quang-Binh Nguyen · Minh Luu · Quang Nguyen · Anh Tran · Khoi Nguyen | style |
| 2 | Wasserstein Style Distribution Analysis and Transform for Stylized Image Generation | Xi Yu · Xiang Gu · Zhihao Shi · Jian Sun | style |
| 3 | RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilation | Yuhan Li · Xianfeng Tan · Wenxiang Shang · Yubo Wu · Jian Wang · Xuanhong Chen · Yi Zhang · Zhu Hangcheng · Bingbing Ni | cloth |
| 4 | HiGarment: Cross-modal Harmony Based Diffusion Model for Flat Sketch to Realistic Garment Image | Junyi Guo · Jingxuan Zhang · Fangyu Wu · Huanda Lu · Qiufeng Wang · Wenmian Yang · ENG LIM · Dongming Lu | garment |
| 5 | NGD: Neural Gradient Based Deformation for Monocular Garment Reconstruction | Soham Dasgupta · Shanthika Naik · Preet Savalia · Sujay Kumar Ingle · Avinash Sharma | garment reconstruction |
| 6 | AIComposer: Any Style and Content Image Composition via Feature Integration | Haowen Li · Zhenfeng Fan · Zhang Wen · Zhengzhou Zhu · Yunjin Li | style |
| 7 | LOTS of Fashion! Multi-Conditioning for Image Generation via Sketch-Text Pairing | Federico Girella · Davide Talon · Ziyue Liu · Zanxi Ruan · Yiming Wang · Marco Cristani | fashion |
| 8 | Multimodal Latent Diffusion Model for Complex Sewing Pattern Generation | Shengqi Liu · Yuhao Cheng · Zhuo Chen · Xingyu Ren · Wenhan Zhu · Lincheng Li · Mengxiao Bi · Xiaokang Yang · Yichao Yan | sewing |
| 9 | Text2Outfit: Controllable Outfit Generation with Multimodal Language Models | Yuanhao Zhai · Yen-Liang Lin · Minxu Peng · Larry Davis · Ashwin Chandramouli · Junsong Yuan · David Doermann | outfit |
| 10 | LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation | Donald Shenaj · Ondrej Bohdal · Mete Ozay · Pietro Zanuttigh · Umberto Michieli | style |
| 11 | UnZipLoRA: Separating Content and Style from a Single Image | Chang Liu · Viraj Shah · Aiyu Cui · Svetlana Lazebnik | style |
| 12 | Pose-Star: Anatomy-Aware Editing for Open-World Fashion Images | Yuran Dong · Mang Ye | fashion |
| 13 | Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks | Hailong Guo · Bohan Zeng · Yiren Song · Wentao Zhang · Jiaming Liu · Chuang Zhang | clothing |
| 14 | All Parts Matter: A Unified Mask-Free Virtual Try-On Framework | Chenghu Du · Shengwu Xiong · Yi Rong | try-on |
| 15 | Magic Insert: Style-Aware Drag-and-Drop | Nataniel Ruiz · Yuanzhen Li · Neal Wadhwa · Yael Pritch · Michael Rubinstein · David Jacobs · Shlomi Fruchter | style |
| 16 | OmniVTON: Training-Free Universal Virtual Try-On | Zhaotong Yang · Yuhui Li · Shengfeng He · Xinzhe Li · Yangyang Xu · Junyu Dong · Yong Du | try-on |
| 17 | PromptDresser: Improving the Quality and Controllability of Virtual Try-On via Generative Textual Prompt and Prompt-aware Mask | Jeongho Kim · Hoiyeong Jin · Sunghyun Park · Jaegul Choo | try-on |
| 18 | Learning Implicit Features with Flow-Infused Transformations for Realistic Virtual Try-On | Delong Zhang · Qiwei Huang · Yang Sun · Yuanliu Liu · Wei-Shi Zheng · Pengfei Xiong · Wei Zhang | try-on |
| 19 | Domain Generalizable Portrait Style Transfer | Xinbo Wang · Wenju Xu · Qing Zhang · Wei-Shi Zheng | style |
| 18 | TextMaster: A Unified Framework for Realistic Text Editing via Glyph-Style Dual-Control | Zhenyu Yan · Jian Wang · Aoqiang Wang · Yuhan Li · Wenxiang Shang · Zhu Hangcheng | style |
| 19 | Tune-Your-Style: Intensity-tunable 3D Style Transfer with Gaussian Splatting | Yian Zhao · rushi ye · Ruochong Zheng · Zesen Cheng · Chaoran Feng · Jiashu Yang · Pengchong Qiao · Chang Liu · Jie Chen | style |
| 20 | SAFT: Shape and Appearance of Fabrics from Template via Differentiable Physical Simulations from Monocular Video | David Stotko · Reinhard Klein | fabric |
| 21 | From Gallery to Wrist: Realistic 3D Bracelet Insertion in Videos | Chenjian Gao, Lihe Ding, Rui Han, Zhanpeng Huang, Zibin Wang, Tianfan Xue | try-on |
SIGGRAPH 2025-Fashion-Related-Papers
| No | Title | Authors | Key words |
|---|---|---|---|
| 1 | Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates | Ren Li, Cong Cao, Corentin Dumery, Yingxuan You, Hao Li, Pascal Fua | Garment Reconstruction |
| 2 | Rags2Riches: Computational Garment Reuse | Anran Qi, Nico Pietroni, Maria Korosteleva, Olga Sorkine-Hornung, Adrien Bousseau | Sewing Pattern Transfer |
| 3 | GarmentImage: Raster Encoding of Garment Sewing Patterns with Diverse Topologies | Yuki Tatsukawa, Anran Qi, I-Chao Shen, Takeo Igarashi | Garment Reconstruction |
| 4 | Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable Physics | Xuan Li, Chang Yu, Wenxin Du, Ying Jiang, Tianyi Xie, Yunuo Chen, Yin Yang, Chenfanfu Jiang | Garment Reconstruction |
| 5 | 3D Stylization via Large Reconstruction Model | Ipek Oztas, Duygu Ceylan, Aysegul Dundar | Style |
| 6 | FashionComposer: Compositional Fashion Image Generation | Sihui Ji, Yiyang Wang, Xi Chen, Xiaogang Xu, Hao Luo, Hengshuang Zhao | Try-on |
CVPR 2025-Fashion-Related-Papers
| No | Title | Authors | Key words |
|---|---|---|---|
| 1 | Text-Driven Fashion Image Editing with Compositional Concept Learning and Counterfactual Abduction | Shanshan Huang · Haoxuan Li · Chunyuan Zheng · Mingyuan Ge · WeiGao · Lei Wang · Li Liu | fashion |
| 2 | Identity-Clothing Similarity Modeling for Unsupervised Clothing Change Person Re-Identification | Zhiqi Pang · Junjie Wang · Lingling Zhao · Chunyu Wang | clothing |
| 3 | K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs | Ziheng Ouyang · Zhen Li · Qibin Hou | style |
| 4 | Geometry in Style: 3D Stylization via Surface Normal Deformation | Nam Anh Dinh · Itai Lang · Hyunwoo Kim · Oded Stein · Rana Hanocka | style |
| 5 | Shining Yourself: High-Fidelity Ornaments Virtual Try-on with Diffusion Model | Yingmao Miao · Zhanpeng Huang · Rui Han · Zibin Wang · Chenhao Lin · Chao Shen | try-on |
| 6 | VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction | Zijian He · Yuwei Ning · Yipeng Qin · Guangrun Wang · Sibei Yang · Liang Lin · Guanbin Li | try-on |
| 7 | SGSST: Scaling Gaussian Splatting Style Transfer | Bruno Galerne · Jianling WANG · Lara Raad · Jean-michel Morel | style |
| 8 | BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training | Xuanpu Zhang · Dan Song · pengxin zhan · Tianyu Chang · Jianhao Zeng · Qing-Guo Chen · Weihua Luo · An-An Liu | try-on |
| 9 | Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction | Dong Li · Wenqi Zhong · Wei Yu · Yingwei Pan · Dingwen Zhang · Ting Yao · Junwei Han · Tao Mei | try-on |
| 10 | Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation | Ruihai Wu · Ziyu Zhu · Yuran Wang · Yue Chen · Jiarui Wang · Hao Dong | garment, embodied |
| 11 | AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models | Xinghui Li · Qichao Sun · Pengze Zhang · Fulong Ye · Zhichao Liao · Wanquan Feng · Songtao Zhao · Qian HE | garment, try-on |
| 12 | Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis | Feng Zhou · Ruiyang Liu · chen liu · Gaofeng He · Yonglu Li · Xiaogang Jin · Huamin Wang | garment |
| 13 | TexGarment: Consistent Garment UV Texture Generation via Efficient 3D Structure-Guided Diffusion Transformer | Jialun Liu · Jinbo Wu · Xiaobo Gao · JiaKui Hu · Bojun Xiong · Xing Liu · Chen Zhao · Hongbin Pei · Haocheng Feng · Yingying Li · Errui Ding · Jingdong Wang | garment |
| 14 | StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer 🌟highlight | ruojun xu · Weijie Xi · Xiaodi Wang · Yongbo Mao · Zach Cheng | style transfer |
| 15 | ChatGarment: Garment Estimation, Generation and Editing via Large Language Models | Siyuan Bian · Chenghao Xu · Yuliang Xiu · Artur Grigorev · Zhen Liu · Cewu Lu · Michael J. Black · Yao Feng | garment geneartion, editing, sewing pattern |
| 16 | ITA-MDT: Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On | Ji Woo Hong · Tri Ton · Trung X. Pham · Gwanhyeong Koo · Sunjae Yoon · Chang D. Yoo | try-on |
| 17 | AIpparel: A Large Multimodal Generative Model for Digital Garments 🌟highlight | Kiyohiro Nakayama · Jan Ackermann · Timur Levent Kesdogan · Yang Zheng · Maria Korosteleva · Olga Sorkine-Hornung · Leonidas Guibas · Guandao Yang · Gordon Wetzstein | garment |
| 18 | Robust-MVTON: Learning Cross-Pose Feature Alignment and Fusion for Robust Multi-View Virtual Try-On | Nannan Zhang · Yijiang Li · Dong Du · Zheng Chong · Zhengwentai Sun · Jianhao Zeng · Yusheng Dai · Zhenyu Xie · Hairui Zhu · Xiaoguang Han | try-on |
| 19 | DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Image | Hyeongjin Nam · Donghwan Kim · Jeongtaek Oh · Kyoung Mu Lee | cloth + body reconstruction |
| 20 | PGC: Physics-Based Gaussian Cloth from a Single Pose 🌟highlight | Michelle Guo · Matt Jen-Yuan Chiang · Igor Santesteban · Nikolaos Sarafianos · Hsiaoyu Chen · Oshri Halimi · Aljaž Božič · Shunsuke Saito · Jiajun Wu · Karen Liu · Tuur Stuyck · Egor Larionov | garment reconstruction, simulation |
| 21 | VTON-HandFit: Virtual Try-on for Arbitrary Hand Pose Guided by Hand Priors Embedding | Yujie Liang · Xiaobin Hu · Boyuan Jiang · Donghao Luo · Xu Peng · Kai WU · Chengming Xu · Wenhui Han · Taisong Jin · Chengjie Wang · Rongrong Ji | try-on |
| 22 | Enhancing Virtual Try-On with Synthetic Pairs and Error-Aware Noise Scheduling | Nannan Li · Kevin Shih · Bryan A. Plummer | try-on |
| 23 | GaPT-DAR: Category-level Garments Pose Tracking via Integrated 2D Deformation and 3D Reconstruction | Li Zhang · mingliang xu · Jianan Wang · Qiaojun Yu · Lixin Yang · Yonglu Li · Cewu Lu · RujingWang · Liu Liu | garment, 3D reconstruction |
| 24 | BootComp: Controllable Human Image Generation with Personalized Multi-Garments | Yisol Choi · Sangkyung Kwak · Sihyun Yu · Hyungwon Choi · Jinwoo Shin | garment, controllable image generation |
| 25 | SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing | Xueting Li, Ye Yuan, Shalini De Mello, Gilles Daviet, Jonathan Leaf, Miles Macklin, Jan Kautz, Umar Iqbal | clothing |
ICLR 2025-Fashion-Related-Papers
| No | Title | Authors | Key words |
|---|---|---|---|
| 1 | CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models | Zheng Chong · Xiao Dong · Haoxiang Li · shiyue Zhang · Wenqing Zhang · Hanqing Zhao · xujie zhang · Dongmei Jiang · Xiaodan Liang | virtual try-on, diffusion models |
| 2 | Attributing Culture-Conditioned Generations to Pretraining Corpora | Huihan Li · Arnav Goel · Keyu He · Xiang Ren | culture-conditioned generation, pretraining corpora |
| 3 | Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On | Siqi Wan · Jingwen Chen · Yingwei Pan · Ting Yao · Tao Mei | virtual try-on, diffusion model, visual correspondence |
If this work is beneficial to your research, please consider citing it or giving this repo a star🌟.
@article{GenAI_in_fashion_Shi,
author = {Shi, Wenda and Wong, Waikeung and Zou, Xingxing},
title = {Generative AI in Fashion: Overview},
journal = {ACM Trans. Intell. Syst. Technol.},
year = {2025},
volume = {16},
number = {4},
articleno = {74},
numpages = {73},
month = jun,
issue_date = {August 2025},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
issn = {2157-6904},
doi = {10.1145/3718098},
url = {https://doi.org/10.1145/3718098}
}
Here we only provide the fashion-centric metrics.
- Image Domain:
- FashionCLIP & FashionSigLip, (marqo-FashionCLIP)
- FashionCLIP & FashionSigLip, (marqo-FashionCLIP)
Only dataset links that returned valid 2xx/3xx HTTP responses during verification are included.
Multi-modal[Text-Image]
| Name | Benchmark | Publication | Task | Scale / Note | Link |
|---|---|---|---|---|---|
| Fashion-200K | Table 3. Benchmarks for Fashion VLP Models | ICCV 2017 | Category retrieval, text-image retrieval | 200K fashion images with short product descriptions. | dataset |
| FashionIQ | Table 3. Benchmarks for Fashion VLP Models | CVPR 2021 | Text-guided image retrieval | 77,684 images across dresses, shirts, and tops with natural-language feedback. | dataset |
Image
| Name | Benchmark | Publication | Task | Scale / Note | Link |
|---|---|---|---|---|---|
| Extended DeepFashion | Table 6. Benchmarks for Fashion Image Generation | ICCV 2017 / CGF 2018 | Image generation, redressing | Upper-body DeepFashion images with text descriptions and body annotations. | dataset |
| FashionTex | Table 6. Benchmarks for Fashion Image Generation | SIGGRAPH 2023 | Fashion image generation | Processed DeepFashion-MultiModal resource used for generation benchmarks. | dataset |
| Polyvore | Table 6. Benchmarks for Fashion Image Generation | ACM MM 2017 | Outfit generation, compatibility | Fashion items and outfits frequently reused for generation benchmarks. | dataset |
| DiFashion | Table 6. Benchmarks for Fashion Image Generation | SIGIR 2024 | Generative outfit recommendation | Benchmark setting built around personalized outfit generation. | dataset |
| iFashion | Table 6. Benchmarks for Fashion Image Generation | KDD 2019 | Outfit recommendation, generation | Pre-defined outfits, fashion items, and user click behaviors. | dataset |
| Polyvore-U | Table 6. Benchmarks for Fashion Image Generation | CVPR 2019 | Outfit recommendation, generation | Polyvore subsets with user-specific outfit/item data. | dataset |
| Dress Code | Table 7. Benchmarks for Fashion Image Editing | ECCV 2022 | Fashion editing, virtual try-on | Garment/person pairs with keypoints, segmentations, and DensePose. | dataset |
| DFMM-Spotlight | Table 7. Benchmarks for Fashion Image Editing | AAAI 2024 | Local fashion editing | Region prompts and masks for tops, pants, outerwear, dresses, and accessories. | dataset |
| VITON | Table 8. Benchmarks for Image-Based Try-On | CVPR 2018 | Image-based virtual try-on | Frontal-view female model and upper-body clothing image pairs. | dataset |
| FashionTryOn | Table 8. Benchmarks for Image-Based Try-On | ACM MM 2019 | Pose-aware virtual try-on | Triplets with clothing images and two human images in different poses. | dataset |
| SAL-HG | Table 8. Benchmarks for Image-Based Try-On | CVPR 2023 | Human-garment landmark benchmark | Re-annotated VITON/VITON-HD/DressCode images with landmarks and visibility attributes. | dataset |
| SHHQ-1.0 | Table 8. Benchmarks for Image-Based Try-On | ECCV 2022 | Full-body try-on, human parsing | High-quality full-body images with segmentation masks, parsing labels, and 2D keypoints. | dataset |
| UPT | Table 8. Benchmarks for Image-Based Try-On | NeurIPS 2021 | On-body garment try-on | Half-body and full-body front-view person images with diverse garment types. | dataset |
| VITON-HD | Table 8. Benchmarks for Image-Based Try-On | CVPR 2021 | High-resolution virtual try-on | 13,679 high-resolution frontal-view woman and upper-body clothing pairs. | dataset |
| MMDGarment | Latest Fashion-Related Papers | ICCV 2025 | Flat sketch to realistic garment image generation | 20,151 garment samples with photos, close-ups, text annotations, and professional flat sketches; part of the dataset is released under access restrictions. | dataset |
| LAION-Garment | Latest Fashion-Related Papers | ICCV 2025 | Versatile image-based virtual try-on | Hugging Face image-text dataset with 84K rows across upper-body, lower-body, and whole-body garment categories. | dataset |
| Garments2Look | Latest Fashion-Related Papers | CVPR 2026 | Outfit-level virtual try-on | 80K many-garments-to-one-look pairs with 3-12 reference garments, 40 major categories, and 300+ fine-grained subcategories. | dataset |
| VRF | Latest Fashion-Related Papers | CVPR 2026 | Person-to-person virtual try-on with visual references | Hugging Face WebDataset with image/text modalities; 83.8K viewer rows and 657K estimated rows. | dataset |
3D
| Name | Benchmark | Publication | Task | Scale / Note | Link |
|---|---|---|---|---|---|
| THuman-2.0 | Table 10. Benchmarks for 3D Clothed Human Generation | CVPR 2021 | 3D clothed human generation | Human scans rendered from 60 views with SMPL-X annotations. | dataset |
| BUFF | Table 10. Benchmarks for 3D Clothed Human Generation | CVPR 2017 | 3D clothed human generation | Textured scans and SMPL sequences of six subjects with six outfits. | dataset |
| DeepCap | Table 10. Benchmarks for 3D Clothed Human Generation | CVPR 2020 | 3D human capture | In-the-wild clothed-human motion sequences with SMPL-style assets. | dataset |
| DynaCap | Table 10. Benchmarks for 3D Clothed Human Generation | SIGGRAPH 2021 | Dynamic 3D human capture | Multi-camera sequences of subjects in several apparel types and motions. | dataset |
| MonoPerfCap | Table 10. Benchmarks for 3D Clothed Human Generation | TOG 2018 | Monocular performance capture | Indoor/outdoor action sequences with varied subject clothing. | dataset |
| LifeScans | Table 10. Benchmarks for 3D Clothed Human Generation | CVPR 2019 | 3D clothed human scans | Static clothed-human scans with SMPL+D-style registration. | dataset |
| RenderPeople | Table 10. Benchmarks for 3D Clothed Human Generation | - | 3D human assets | Commercial 4D people assets used as clothed-human resources. | dataset |
| AXYZ | Table 10. Benchmarks for 3D Clothed Human Generation | - | 3D human assets | Commercial 3D people assets referenced as clothed-human resources. | dataset |
| Digital Wardrobe | Table 12. Benchmarks for 3D Garment Generation | ICCV 2019 | 3D garment generation | Registered 3D scans with SMPL body and garment segmentation labels. | dataset |
| Deep Fashion3D | Table 12. Benchmarks for 3D Garment Generation | ECCV 2020 | 3D garment reconstruction | 563 garment items with feature lines, body poses, multiview images, and textures. | dataset |
| GarVerse-LOD | Table 12. Benchmarks for 3D Garment Generation | SIGGRAPH Asia 2024 | 3D garment generation | Hierarchical garment dataset with multiple levels of detail. | dataset |
| Wang et al. | Table 13. Benchmarks for Sewing Pattern Generation | SIGGRAPH Asia 2018 | Sewing pattern generation | 2D sketches, garment/body parameters, and draped 3D garment shapes. | dataset |
| Korosteleva and Lee | Table 13. Benchmarks for Sewing Pattern Generation | NeurIPS 2021 | Sewing pattern generation | Garment design variations draped over bodies with 3D models and segmentation labels. | dataset |
| SewFactory | Table 13. Benchmarks for Sewing Pattern Generation | SIGGRAPH Asia 2023 | Sewing pattern generation | Paired images, human pose/shape, DensePose, sewing patterns, garment meshes, depth, and normals. | dataset |
| GarmentCodeData | Table 13. Benchmarks for Sewing Pattern Generation | ECCV 2024 | Sewing pattern generation | Large synthetic garment set with sewing patterns, draped meshes, UV maps, and measurements. | dataset |
| MPV-3D | 4.4.2 Benchmark Datasets | ICCV 2021 | 3D virtual try-on | Person-clothes image pairs with associated depth maps for 3D try-on. | dataset |
| AMASS | 4.4.2 Benchmark Datasets | ICCV 2019 | 3D body motion for try-on | Body meshes and motion data used with garment datasets for collision evaluation. | dataset |
| TailorNet | 4.4.2 Benchmark Datasets | CVPR 2020 | 3D garments for try-on | Garment assets paired with body meshes for body-garment collision evaluation. | dataset |
| ReWeaver-GCD-TS | Latest Fashion-Related Papers | CVPR 2026 | Topology-accurate garment reconstruction | 100K+ synthetic samples with multi-view RGB images, 3D garment geometries, textured human body meshes, and annotated sewing patterns. | dataset |
| GarmageSet | Latest Fashion-Related Papers | SIGGRAPH Asia 2025 | Generic 3D garment modeling | 14,801 professionally curated garments spanning major clothing categories with detailed structural and style annotations. | dataset |
| GCD-MM | Latest Fashion-Related Papers | CVPR 2025 | Multimodal digital garment generation | GarmentCodeData-Multimodal annotations for 120K+ garments with text, images, sewing patterns, and editing instructions. | dataset |
Dynamic[Video/3D Animation]
| Name | Benchmark | Publication | Task | Scale / Note | Link |
|---|---|---|---|---|---|
| ReSynth | Table 14. Benchmarks for 3D Clothed Human Animation | ICCV 2021 | Clothed human animation | Pose-dependent clothing deformation over varied outfits and poses. | dataset |
| ClothSeq | Table 14. Benchmarks for 3D Clothed Human Animation | ICCV 2021 | Loose-clothing animation | Subjects wearing loose clothes with sequences of 500-750 frames. | dataset |
| THuman-CloSET | Table 14. Benchmarks for 3D Clothed Human Animation | CVPR 2023 | Clothed human animation | Loose clothing, sparse poses, and challenging outfit categories. | dataset |
| AGORA | Table 14. Benchmarks for 3D Clothed Human Animation | CVPR 2021 | Clothed human animation | High-resolution images with ground-truth 3D bodies in natural clothing and scenes. | dataset |
| VTO | Table 15. Benchmarks for 3D Garment Animation | CGF 2019 | 3D garment animation | Dressed character animations with diverse motions and body shapes. | dataset |
| VirtualBones | Table 15. Benchmarks for 3D Garment Animation | SIGGRAPH 2022 | Garment animation | Garments driven by avatar motion under varied simulation parameters. | dataset |
| D-LAYERS | Table 15. Benchmarks for 3D Garment Animation | ICCV 2023 | Multi-layer garment animation | Multi-layered garment dynamics with human motion and random wind. | dataset |
| CLOTH3D++ | Table 15. Benchmarks for 3D Garment Animation | NeurIPS 2020 Competition Track | Garment dynamics | RGBA video sequences paired with 3D data for garment dynamics. | dataset |
| CLOTH4D | Table 15. Benchmarks for 3D Garment Animation | CVPR 2023 | 4D garment animation | 100K+ clothed meshes, paired unclothed humans, and fashion-design-standard outfits. | dataset |
| 4D-Dress | Table 15. Benchmarks for 3D Garment Animation | CVPR 2024 | 4D clothed human capture | 64 outfits in 520 motion sequences with textured scans, SMPL-X, and garment meshes. | dataset |
| Sizer | Table 17. Benchmarks for Draping | ECCV 2020 | Garment draping | 100 subjects with clothing size variation and realistic cloth deformations. | dataset |
| CLOTH3D | Table 17. Benchmarks for Draping | ECCV 2020 | Garment draping | Large-scale 3D clothing on posed SMPL bodies with varied topology and fabric. | dataset |
| UBC fashion video | Table 18. Benchmarks for Video-Based Virtual Try-On | BMVC 2019 | Video-based virtual try-on | 600 fashion videos with diverse clothing and high-resolution static-camera captures. | dataset |
| TikTok dataset | Table 18. Benchmarks for Video-Based Virtual Try-On | CVPR 2021 | Video-based virtual try-on | Dance videos with human masks and UV coordinates. | dataset |
| Dance50k | Table 18. Benchmarks for Video-Based Virtual Try-On | CVPR 2022 | Video generation, virtual try-on | 50K dance videos with varied poses and garment types. | dataset |
| ViT-HD | Latest Fashion-Related Papers | CVPR 2026 | High-definition video virtual try-on | 15,070 high-quality video samples at 810x1080 resolution, covering 178 diverse garment styles. | dataset |
| MV-Fashion | Latest Fashion-Related Papers | CVPR 2026 | Multi-view virtual try-on, size estimation, novel view synthesis | 3,273 multi-view video sequences with 72.5M frames from 80 subjects and 474 outfit sets. | dataset |
| BarbieGait | Latest Fashion-Related Papers | CVPR 2026 | Cloth-changing synthetic human gait recognition | Identity-consistent synthetic human dataset with versatile cloth-changing; access requires submitting the dataset agreement. | dataset |
The following sections follow the taxonomy introduced in Generative AI in Fashion: Overview.
Summary developments of technology
| Title | Publication | Paper | Key Word | Region |
|---|---|---|---|---|
| Computational Technologies for Fashion Recommendation: A Survey | ACM Comput. Surv. | paper | Fashion Recommendation | Hong Kong |
| A Review of Modern Fashion Recommender Systems | ACM Comput. Surv. | paper | Fashion Recommendation | Italy |
| A survey on Fashion Image Retrieval | ACM Comput. Surv. | paper | Fashion Retrieval | India |
| Appearance and Pose-Guided Human Generation: A Survey | ACM Comput. Surv. | paper | Fashion Generation | Hong Kong |
| Analytics Applications in Fashion Supply Chain Management—A Review of Literature and Practice | IEEE Trans Eng Manag | paper | Fashion Supply Chain | Germany |
Evaluation protocols for specific tasks
| Title | Publication | Paper | Link | Region |
|---|---|---|---|---|
| How Good Is Aesthetic Ability of a Fashion Model? | CVPR 2022 | paper | dataset | Hong Kong |
| Where are my clothes? A multi-level approach for evaluating deep instance segmentation architectures on fashion images | CVPRW 2021 | paper | - | France |
| Assessing Fashion Recommendations: A Multifaceted Offline Evaluation Approach | recsysXfashion 2019 | paper | - | USA |
Understanding of fashion images
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| SyncMask | SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining | CVPR 2024 | paper | - | South Korea |
| FAME-ViL | FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks | CVPR 2023 | -> | project | UK |
| FashionSAP | FashionSAP: Symbols and Attributes Prompt for Fine-grained Fashion Vision-Language Pre-training | CVPR 2023 | -> | project | China |
| MVLT | Masked Vision-language Transformer in Fashion | MIR 2023 | paper | - | China |
| OpenFashionCLIP | OpenFashionCLIP: Vision-and-Language Contrastive Learning with Open-Source Fashion Data | ICIAP 2023 | -> | project | Italy |
| - | A fine-grained vision and language representation framework with graph-based fashion semantic knowledge | CAD/Graphics 2023 | paper | - | China |
| FashionCLIP | Contrastive language and vision learning of general fashion concepts | Scientific Reports (2022) | paper | code | Canada |
| FashionViL | Fashion-Focused Vision-and-Language Representation Learning | ECCV 2022 | -> | project | UK |
| Kaleido-BERT | Kaleido-BERT: Vision-Language Pre-Training on Fashion Domain | CVPR 2021 | paper | - | China |
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| - | Progressive One-shot Human Parsing | AAAI 2021 | paper | - | Sydney |
| SIZER | SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing | ECCV 2020 | paper | project | Germany |
| - | Hierarchical Human Parsing With Typed Part-Relation Reasoning | CVPR 2020 | paper | code | Switzerland |
| Look into Person | Look into Person: Joint Body Parsing & Pose Estimation Network and a New Benchmark | TPAMI 2019 | paper | - | China |
| - | Surveillance Video Parsing With Single Frame Supervision | CVPR 2017 | paper | - | China |
| - | Clothes Co-Parsing Via Joint Image Segmentation and Labeling With Application to Clothing Retrieval | TMM 2016 | paper | - | China |
| - | Parsing Based on Parselets: A Unified Deformable Mixture Model for Human Parsing | TPAMI 2015 | paper | - | Singapore |
| - | Retrieving Similar Styles to Parse Clothing | TPAMI 2014 | paper | - | Japan |
| - | Fashion Parsing with Video Context | MM 2014 | paper | - | Singapore |
| - | Paper Doll Parsing: Retrieving Similar Styles to Parse Clothing Items | ICCV 2013 | paper | - | USA |
| - | Fashion Parsing With Weak Color-Category Labels | TMM 2013 | paper | - | Singapore |
| - | Parsing clothing in fashion photographs | CVPR 2012 | paper | - | USA |
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| - | DETR-based Layered Clothing Segmentation and Fine-Grained Attribute Recognition | CVPRW 2023 | paper | - | Hong Kong |
| Fashionformer | Fashionformer: A Simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition | ECCV 2022 | -> | project | China |
| Fashionpedia | Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset | ECCV 2020 | paper | - | USA |
| - | Joint Multi-Person Pose Estimation and Semantic Part Segmentation | CVPR 2017 | paper | - | USA |
| DeepFashion | DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations | CVPR 2016 | paper | - | Hong Kong |
| - | Who Blocks Who: Simultaneous clothing segmentation for grouping images | ICCV 2011 | paper | - | China |
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| - | Improving apparel detection with category grouping and multi-grained branches | Multimedia Tools and Applications 2022 | paper | - | USA |
| CoRe | CoRe: Color Regression for Multicolor Fashion Garments | CVPRW 2022 | paper | - | France |
| - | Spatial-aware non-local attention for fashion landmark detection | ICME 2019 | paper | - | China |
| - | Layout-Graph Reasoning for Fashion Landmark Detection | CVPR 2019 | paper | - | China |
| DeepFashion2 | DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images | CVPR 2019 | paper | - | China |
| - | A global-local embedding module for fashion landmark detection | ICCVW 2019 | paper | - | Korea |
| - | Unconstrained Fashion Landmark Detection via Hierarchical Recurrent Transformer Networks | MM 2017 | paper | - | Hong Kong |
| - | Fashion Landmark Detection in the Wild | ECCV 2016 | paper | - | Hong Kong |
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| GarmentTracking | GarmentTracking: Category-Level Garment Pose Tracking | CVPR 2023 | -> | project | China |
| GarmentNets | GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completion | ICCV 2021 | -> | project | USA |
Online selling
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| M3-Net | Learning Attribute and Class-Specific Representation Duet for Fine-grained Fashion Analysis | CVPR 2023 | paper | - | USA |
| MODC | Fine-grained Fashion Representation Learning by Online Deep Clustering | ECCV 2022 | paper | - | USA |
| FashionVLP | FashionVLP: Vision Language Transformer for Fashion Retrieval with Feedback | CVPR 2022 | paper | - | USA |
| EI-CLIP | EI-CLIP: Entity-aware Interventional Contrastive Learning for E-commerce Cross-modal Retrieval | CVPR 2022 | paper | - | USA |
| DAtRNet | DAtRNet: Disentangling Fashion Attribute Embedding for Substitute Item Retrieval | CVPRW 2022 | paper | - | India |
| UIGR | UIGR: Unified Interactive Garment Retrieval | CVPRW 2022 | paper | code | UK |
| CIRPLANT | Image Retrieval on Real-Life Images With Pre-Trained Vision-and-Language Models | ICCV 2021 | paper | - | Australia |
| Fashion IQ | Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback | CVPR 2021 | paper | - | USA |
| - | Interpretable Multimodal Retrieval for Fashion Products | MM 2018 | paper | - | Singapore |
| DARN | Cross-Domain Image Retrieval with a Dual Attribute-Aware Ranking Network | ICCV 2015 | paper | - | Singapore |
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| Fashion-GPT | Fashion-GPT: Integrating LLMs with Fashion Retrieval System | LGM3A '23 (MM 2023 workshop) | paper | - | Singapore |
| FashionVQA | FashionVQA: A Domain-Specific Visual Question Answering System | CVPRW 2023) | paper | - | USA |
| VSE | Fashion-Specific Ambiguous Expression Interpretation with Partial Visual-Semantic Embedding | CVPRW 2023) | paper | - | Japan |
| - | A Conversational Shopping Assistant for Online Virtual Stores | MM 2022 | paper | - | Portugal |
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| wFlow | Dressing in the Wild by Watching Dance Videos | CVPR 2022 | -> | project | China |
| ClothFormer | ClothFormer: Taming Video Virtual Try-on in All Module | CVPR 2022 | -> | project | China |
Personal Styling
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| FCBoost-Net | FCBoost-Net: A Generative Network for Synthesizing Multiple Collocated Outfits via Fashion Compatibility Boosting | MM 2023 | paper | - | China |
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| CP-TransMatch | Modeling Multi-Relational Connectivity for Personalized Fashion Matching | MM 2023 | paper | - | Hong Kong |
| SHIFT15M | SHIFT15M: Fashion-specific dataset for set-to-set matching with several distribution shifts | CVPRW 2023) | paper | code | Japan |
| BiHGH | Bi-directional Heterogeneous Graph Hashing towards Efficient Outfit Recommendation | MM 2022 | paper | - | Australia |
| OutfitTransformer | OutfitTransformer: Outfit Representations for Fashion Recommendation | CVPRW 2022 | paper | - | USA |
| OutfitGAN | OutfitGAN: Learning Compatible Items for Generative Fashion Outfits | CVPRW 2022 | paper | - | USA |
| GradREC | “Does it come in black?” CLIP-like models are zero-shot recommenders | ECNLP 5(ACL 2022 workshop) | paper | code | Milan |
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| StyleMe | StyleMe: Towards Intelligent Fashion Generation with Designer Style | CHI 2023 | paper | code | China |
| AI Archive | Generative AI for Concept Creation in Footwear Design | INVITED-TALK (SIGGRAPH 2023) | paper | - | Germany |
| UnitedHuman | UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generation | ICCV 2023 | -> | project | China |
| FreeDoM | FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model | ICCV 2023 | paper | code | China |
| BoxDiff | BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion | ICCV 2023 | paper | code | Singapore |
| ControlNet | Adding Conditional Control to Text-to-Image Diffusion Models | ICCV2023 | paper | code | USA |
| PromptStyler | PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization | ICCV 2023 | -> | project | South Korea |
| Diffusart | Diffusart: Enhancing Line Art Colorization with Conditional Diffusion Models | CVPRW 2023 | paper | - | France |
| Gatha | Gatha: Relational Loss for enhancing text-based style transfer | CVPRW 2023 | paper | - | USA |
| DiffFashion | Image Reference-guided Fashion Design with Structure-aware Transfer by Diffusion Models | CVPRW 2023 | paper | code | China |
| VectorFusion | VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models | CVPR 2023 | -> | project, unofficial code | USA |
| DiffSketcher | DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models | NIPS 2023 | -> | project | China |
| SGDiff | SGDiff: A Style Guided Diffusion Model for Fashion Synthesis | MM 2023 | paper | code | Hong Kong |
| FashionDiff | FashionDiff: A Controllable Diffusion Model Using Pairwise Fashion Elements for Intelligent Design | MM 2023 | paper | - | China |
| InspirNET | InspirNET: An Unsupervised Generative Adversarial Network with Controllable Fine-grained Texture Disentanglement for Fashion Generation | MM 2023 | paper | - | China |
| - | Toward Intelligent Interactive Design: A Generation Framework Based on Cross-domain Fashion Elements | MM 2023 | paper | - | China |
| - | Normal-guided Garment UV Prediction for Human Re-texturing | CVPR 2023 | paper | - | USA |
| TemporalUV | TemporalUV: Capturing Loose Clothing with Temporally Coherent UV Coordinates | CVPR 2022 | paper | - | Germany |
| ARMANI | ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design | MM 2022 | paper | - | China |
| AI Carpet | AI Carpet: Automatic Generation of Aesthetic Carpet Pattern | MM 2022 | paper | - | China |
| Wearable ImageNet | Wearable ImageNet: Synthesizing Tileable Textures via Dataset Distillation | CVPRW 2022 | paper | project | USA |
| Rank in Style | Rank in Style: A Ranking-based Approach to Find Interpretable Directions | CVPRW 2022 | paper | - | Turkey |
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| FashionTex | FashionTex: Controllable Virtual Try-on with Text and Texture. | SIGGRAPH 2023 | paper | code | China |
| FreqHPT | FreqHPT: Frequency-aware attention and flow fusion for Human Pose Transfer | CVPRW 2023) | paper | - | China |
| SAL-VTON | Linking Garment with Person via Semantically Associated Landmarks for Virtual Try-On | CVPR 2023 | paper | project | China |
| TryOnDiffusion | TryOnDiffusion: A Tale of Two UNets | CVPR 2023 | -> | project | USA |
| GP-VTON | GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning | CVPR 2023 | -> | project | China |
| LaDI-VTON | LaDI-VTON:Latent Diffusion Textual-Inversion Enhanced Virtual Try-On | MM 2023 | paper | code | Italy |
| DCI-VTON | Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow | MM 2023 | paper | code | China |
| PG-VTON | PG-VTON: A Novel Image-Based Virtual Try-On Method via Progressive Inference Paradigm | TMM 2023 | paper | code | China |
| DOC-VTON | OccluMix: Towards De-Occlusion Virtual Try-on by Semantically-Guided Mixup | TMM 2023 | paper | code | China |
| - | A High-resolution Image-based Virtual Try-on System in Taobao E-commerce Scenario | MM 2022 | paper | - | China |
| GT-MUST | GT-MUST: Gated Try-on by Learning the Mannequin-Specific Transformation | MM 2022 | paper | - | China |
| PL-VTON | Progressive Limb-Aware Virtual Try-On | MM 2022 | paper | - | China |
| Dress Code | Dress Code: High-Resolution Multi-Category Virtual Try-On | CVPRW 2022 | paper | project | Italy |
| DBCT | Dual-Branch Collaborative Transformer for Virtual Try-On | CVPRW 2022 | paper | - | Italy |
| DP-VTON | Towards Detailed Characteristic-Preserving Virtual Try-On | CVPRW 2022 | paper | - | South Korea |
| Flow-Style-VTON | Style-Based Global Appearance Flow for Virtual Try-On | CVPR 2022 | -> | project | UK |
| RT-VTON | Full-Range Virtual Try-On with Recurrent Tri-Level Transform | CVPR 2022 | -> | project | China, Singapore |
| DGP | Weakly Supervised High-Fidelity Clothing Model Generation | CVPR 2022 | paper | - | China |
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| Patternshop | Patternshop: Editing Point Patterns by Image Manipulation | SIGGRAPH 2023 | -> | project | Germany |
| MGD | Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing | ICCV 2023 | paper | code | Italy |
| EditAnything | EditAnything: Empowering Unparalleled Flexibility in Image Editing and Generation | MM 2023 | paper | project | China |
| SketchEdit | SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches | CVPR 2022 | -> | project | USA |
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| FashionMatrix | Fashion Matrix: Editing Photos by Just Talking | Preprint 2023 | -> | project | China |
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| Garment Particles | Garment Particles: A 2D-3D Symmetric Garment Representation for Generation and Editing | SIGGRAPH 2026 | paper | project | Japan, USA |
| Garment3DGen | Garment3DGen: 3D Garment Stylization and Texture Generation | 3DV 2025 | -> | project | USA |
| En3D | En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data | CVPR 2024 | -> | project | China |
| SewFormer | Towards Garment Sewing Pattern Reconstruction from a Single Image | TOG (SIGGRAPH Asia 2023) | -> | project | Singapore |
| GTA | Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction | NIPS 2023 | -> | project | China |
| SeSDF | SeSDF: Self-evolved Signed Distance Field for Implicit 3D Clothed Human Reconstruction | CVPR 2023 | paper | - | Hong Kong |
| SoY | Shape of You: Precise 3D shape estimations for diverse body types | CVPRW 2023) | paper | - | USA |
| KBody | KBody: Balanced monocular whole-body estimation | CVPRW 2023) | paper | project | USA |
| CAR | High-Fidelity Clothed Avatar Reconstruction from a Single Image | CVPR 2023 | -> | project | China |
| DIFu | DIFu: Depth-Guided Implicit Function for Clothed Human Reconstruction | CVPR 2023 | -> | project | South Korea |
| NeuralUDF | NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologies | CVPR 2023 | -> | project | Hong Kong |
| REC-MV | REC-MV: REconstructing 3D Dynamic Cloth from Monocular Videos | CVPR 2023 | -> | project | China |
| Get3DHuman | Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-aligned Reconstruction Priors | ICCV2023 | -> | project | China |
| HairStep | HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling | CVPR 2023 | -> | project | China |
| ECON | ECON: Explicit Clothed humans Optimized via Normal integration | CVPR 2023 | -> | project | Germany |
| DrapeNet | DrapeNet: Garment Generation and Self-Supervised Draping | CVPR 2023 | -> | project | Switzerland |
| AnchorDEF | Learning Anchor Transformations for 3D Garment Animation | CVPR 2023 | -> | project | China |
| CloSET | CloSET: Modeling Clothed Humans on Continuous Surface with Explicit Template Decomposition | CVPR 2023 | -> | project | China |
| - | Clothed Human Performance Capture with a Double-layer Neural Radiance Fields | CVPR 2023 | paper | - | China |
| HOOD | HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics | CVPR 2023 | -> | project | Switzerland |
| xCloth | xCloth: Extracting Template-free Textured 3D Clothes from a Monocular Image | MM 2023 | paper | - | India |
| AvatarFusion | AvatarFusion: Zero-shot Generation of Clothing-Decoupled 3D Avatars Using 2D Diffusion | MM 2023 | paper | project | China |
| Control3D | Control3D: Towards Controllable Text-to-3D Generation | MM 2023 | paper | - | China |
| SynBody | SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling | ICCV 2023 | -> | project | China |
| EVA3D | EVA3D: Compositional 3D Human Generation from 2D Image Collections | ICLR 2023 | -> | project | Singapore |
| ReFU | A Repulsive Force Unit for Garment Collision Handling in Neural Networks | ECCV 2022 | -> | project | USA |
| SNUG | SNUG: Self-Supervised Neural Dynamic Garments | CVPR 2022 | -> | project | Spain |
| ICON | ICON: Implicit Clothed humans Obtained from Normals | CVPR 2022 | -> | project | Germany |
| True Seams | True Seams:Modeling Seams in Digital Garments | SIGGRAPH 2022 | -> | project | USA |
| VirtualBones | Predicting Loose-Fitting Garment Deformations Using Bone-Driven Motion Networks | SIGGRAPH 2022 | -> | project | China |
| CrossHuman | CrossHuman: Learning Cross-guidance from Multi-frame Images for Human Reconstruction | MM 2022 | paper | - | China |
| ReEF | Registering Explicit to Implicit: Towards High-Fidelity Garment mesh Reconstruction from Single Images | CVPR 2022 | -> | project | China |
| PHORHUM | Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing | CVPR 2022 | -> | project | USA |
| NeuralTailor | NeuralTailor: Reconstructing Sewing Pattern Structures from 3D Point Clouds of Garments | SIGGRAPH 2022 | paper | - | South Korea |
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| WordRobe | WordRobe: Text-Guided Generation of Textured 3D Garments | ECCV 2024 | paper | project | India |
| CLOTH4D | CLOTH4D: A Dataset for Clothed Human Reconstruction | CVPR 2023 | -> | project | Hong Kong |
| Garment4D | Garment4D: Garment Reconstruction from Point Cloud Sequences | NIPS 2021 | -> | project | Singapore |
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| POP | POP: Mining POtential Performance of new fashion products via webly cross-modal query expansion | ECCV 2022 | -> | project | Italy |
| Visuelle 2.0 | The multi-modal universe of fast-fashion: the Visuelle 2.0 benchmark | CVPRW 2022 | paper | project | Italy |
| Model | Title | Publication | Paper | Link | Region |
|---|---|---|---|---|---|
| - | Multimodal Fashion Knowledge Extraction as Captioning | SIGIR-AP 2023 | paper | - | Hong Kong |
| - | Who, Where, and What to Wear?: Extracting Fashion Knowledge from Social Media | MM 2019 | paper | - | Singapore |
| - | Describing Clothing by Semantic Attributes | ECCV 2012 | paper | - | USA |
- Workshop on Virtual Try-On (CVPR Workshop): CV_VTO 2024
- Computer Vision for Fashion, Art, and Design (CVPR Workshop): CVFAD 2024, CVFAD 2023, CVFAD 2022
- Workshop on Creativity & Generative AI (NeurIPS Workshop): Creat&GenAI 2024
- Machine Learning for Creativity and Design (NeurIPS Workshop): ML4CD 2023, ML4CD 2022
- Creative AI Across Modalities (AAAI Workshop): creativeAI 2023
- Multimedia Computing towards Fashion Recommendation (ACM MM Workshop): MCFR 2022
- recsysXfashion (RecSys Workshop): recsysXfashion 2022, recsysXfashion 2021
| Name | Found | Info | News |
|---|---|---|---|
| CALA | 2016 | fashion supply chain interface that unifies design, development, production, and logistics | 2022.11 |
| Zalando Research | 2016 | Research | 2023.04 fashion assistant powered by ChatGPT |
| Vue.ai | 2016 | Retail AI analysis, AI avatar | - |
| 极睿 infimind | 2017 | Fashion Product Content | 2023.11 interview in mandarin |
| 知衣 zhiyi | 2018 | Fashion Design Collaboration | 2023.08 Fashion Diffusion |
| LALALAND | 2019 | AI avatar, Fashion Product Content | 2023.08 collaborate with Browzwear-VStitcher |
| PatternedAi | 2021 | Pattern Design | - |
| Dsign.Ai | - | Prints and Patterns Design | - |
| AIMDE-Symmpix | 2023 | Fashion Pattern, 3D | 2023.11 new feature |
| Weshop | 2023 | AI avatar & Fashion Product Content | a subsidiary of MOGU |
| Wondershare VirtuLook | 2023 | AI avatar & Fashion Product Content | a subsidiary of wondershare |
| Pixelcut | 2022 | AI-powered editing tools(Product Content) | - |
| CreatorKit | 2020 | AI Product Content, Videos | - |
| DeepImage | 2022 | AI Product Content | - |
| Unbound | - | personal AI business assistant | - |
| Zeg AI | 2018 | AI Product Content, Videos, 3D Render | - |
| Group/Lab/Univ | Researchers |
|---|---|
| AiDlab-PolyU | Calvin WONG,Xingxing Zou |
| GAP Lab-CUHKSZ | Xiaoguang Han |
| HCP-I2 Lab-SYSU | Xiaodan Liang,Zhenyu Xie |
| HIT SZ | Haijun Zhang |
| MMLab-NTU | Ziwei Liu |
| MPI-IS | Michael Black |
| Meshcapade | Maria Korosteleva |
| CVLab-EPFL | Ren Li |
| AImageLab | Rita Cucchiara |
| Utah Univ | Ziad Al-Halah |
| Georgia Tech | Devi Parikh |
| UT Austin | Kristen Grauman |
| Cornell | Kavita Bala |
| UIUC | Ranjitha Kumar |
Other Resources
- Generative AI’s Act Two | SEQUOIA | 2023.09
- How Are Consumers Using Generative AI?| A16Z | 2023.09
- Outlook for the Global and Chinese Fashion Industry in 2035|Roland Berger|2023.08
- The Complete Playbook for Generative AI in Fashion|Bof|2023.06
- Generative AI: Unlocking the future of fashion |McKinsey|2023.03
- Fashion Datasets
- Cool Fashion Papers(Before 2022)
- awesome-fashion-ai
- AI4Design Survey
- image-to-image-papers
- Awesome Virtual Try-on (VTON) Research
- Awesome-pose-transfer
- Human Body Reconstruction
- The Roadmap of Generative AI
- awesome-Ai-tools
- LLM Survey
- LLM-Agent-Paper-List
- Awesome-diffusion-model-for-image-processing
- Multimodal Image Synthesis and Editing: The Generative AI Era
- GAN-Inversion Survey
- A Survey on Deep Generative 3D-aware Image Synthesis
- Awesome 3D Generation
- Generative AI meets 3D: A Survey on Text-to-3D in AIGC Era
- Awesome GenAI Tech
