Research map / Image generation / Editing and style transfer
Weakly Supervised High-Fidelity Clothing Model Generation
Ruili Feng, Cheng Ma, Chengji Shen, Xin Gao, Zhenjiang Liu, Xiaobo Li, Kairi Ou, Deli Zhao, Zheng-Jun Zha
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use DGP instead of VITON-HD | Clothing model generation · CMI, 512×512 | FID: 87.5 -> 51.6 | Improved |
| Use DGP instead of VITON-HD | Clothing model generation · CMI, 512×512 | SWD: 56.1 -> 22.4 | Improved |
| Use DGP instead of VITON-HD | Clothing model generation · MPV, 512×512 | FID: 40.6 -> 48.4 | Hurt |
| Use DGP instead of VITON-HD | Clothing model generation · MPV, 512×512 | SWD: 52.7 -> 36.7 | Improved |
| Use DGP instead of PF-AFN | Clothing model generation · CMI, 128×128 | FID: 86.6 -> 56.5 | Improved |
| Use DGP instead of PF-AFN | Clothing model generation · CMI, 128×128 | SWD: 29.4 -> 18.8 | Improved |
| Use DGP instead of VITON-HD | Clothing model generation · MPV, 128×128 | FID: 44.7 -> 46.8 | Hurt |
| Use DGP instead of PF-AFN | Clothing model generation · MPV, 128×128 | SWD: 24.9 -> 29.9 | Hurt |
| Add semantic search after projection (ablation) | DGP · CMI | FID: 54.2 -> 52.9 | Improved |
| Add semantic search after projection (ablation) | DGP · CMI | SWD: 56.7 -> 45.7 | Improved |
| Add pattern search (ablation) | DGP · CMI | FID: 52.9 -> 58.9 | Hurt |
| Add pattern search (ablation) | DGP · CMI | SWD: 45.7 -> 46.5 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- VITON-HD — VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization (CVPR 2021) · better on 3 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- A Generative Model of People in Clothing (ICCV 2017 · similarity 0.89)
- GAN-based Garment Generation Using Sewing Pattern Images (ECCV 2020 · similarity 0.89)
- Be Your Own Prada: Fashion Synthesis With Structural Coherence (ICCV 2017 · similarity 0.89)
- DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images (NeurIPS 2026 · similarity 0.87)
- Design2Cloth: 3D Cloth Generation from 2D Masks (CVPR 2024 · similarity 0.87)
- DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
