Research map / Label-efficient and robust learning / Self-supervised and contrastive
Greatness in Simplicity: Unified Self-Cycle Consistency for Parser-Free Virtual Try-On
Chenghu Du, junyin Wang, Shuqing Liu, Shengwu Xiong
Read the paperCheck 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 |
|---|---|---|---|
| add auxiliary deformer GA in NGD (ablation) | USC-PFN NGD · VITON unpaired | FID: 42.23 -> 25.44 | Improved |
| add data term Edat in MRF (ablation) | USC-PFN NGD · VITON unpaired | FID: 30.53 -> 25.44 | Improved |
| add MRF module (ablation) | USC-PFN SIG · VITON unpaired | FID: 14.28 -> 10.47 | Improved |
| add Lsr skin supervision loss (ablation) | USC-PFN SIG · VITON unpaired | FID: 15.44 -> 10.47 | Improved |
| USC-PFN parser-free self-cycle vs in-painting SDAFN | USC-PFN · VITON paired | SSIM: 0.88 -> 0.91 | Improved |
| USC-PFN vs knowledge distillation PF-AFN | USC-PFN · VITON paired | SSIM: 0.89 -> 0.91 | Improved |
| USC-PFN vs cycle consistency DCTON | USC-PFN · VITON paired | SSIM: 0.83 -> 0.91 | Improved |
| USC-PFN vs cycle consistency DCTON | USC-PFN · VITON unpaired | FID: 14.82 -> 10.47 | Improved |
| USC-PFN vs in-painting RT-VTON | USC-PFN · VITON unpaired | FID: 11.66 -> 10.47 | Improved |
| USC-PFN vs knowledge distillation PF-AFN | USC-PFN · VITON unpaired | FID: 10.09 -> 10.47 | Hurt |
| USC-PFN vs ACGPN inference speed | USC-PFN · VITON | FPS: 10 -> 39 | Improved |
| USC-PFN vs DCTON FLOPs | USC-PFN · VITON | FLOPs: 194G -> 46G | Improved |
Closest papers by meaning
- CycleVTON: A Cycle Mapping Framework for Parser-Free Virtual Try-On (AAAI 2024 · similarity 0.94)
- Disentangled Cycle Consistency for Highly-Realistic Virtual Try-On (CVPR 2021 · similarity 0.94)
- Arbitrary Virtual Try-on Network: Characteristics Representation and Trade-off between Body and Clothing (ICLR 2023 · similarity 0.91)
- Full-Range Virtual Try-On With Recurrent Tri-Level Transform (CVPR 2022 · similarity 0.91)
- Enhancing Virtual Try-On with Synthetic Pairs and Error-Aware Noise Scheduling (CVPR 2025 · similarity 0.90)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 2025 · similarity 0.89)
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.
