Research map / Image generation / Editing and style transfer
Virtual Try-On with Pose-Garment Keypoints Guided Inpainting
Zhi Li, Pengfei Wei, Xiang Yin, Zejun Ma, Alex C. Kot
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 |
|---|---|---|---|
| condition inpainting on the target segmentation map (ablation) | KGI · VITON-HD paired 512x384 | FID: 8.22 -> 6.50 | Improved |
| condition inpainting on warped garment (ablation) | KGI · VITON-HD paired 512x384 | FID: 14.34 -> 6.50 | Improved |
| increase inference diffusion steps from 5 to 50 (ablation) | KGI · VITON-HD paired 512x384 | FID: 8.81 -> 6.50 | Improved |
| keypoint-guided inpainting instead of HR-VITON pipeline | HR-VITON · VITON-HD paired 1024x768 | FID: 10.91 -> 6.93 | Improved |
| keypoint-guided inpainting instead of HR-VITON pipeline | HR-VITON · VITON-HD paired 256x192 | LPIPS: 0.062 -> 0.062 | No clear effect |
| keypoint-guided inpainting instead of HR-VITON pipeline | HR-VITON · VITON-HD unpaired 1024x768 | FID: 11.03 -> 10.33 | Improved |
| split garment into five sub-segments for keypoint-guided TPS warping | KGI garment warping · qualitative | garment shape distortion at overlaps | Improved |
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 2 of 2 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
- Toward Realistic Virtual Try-on Through Landmark Guided Shape Matching (AAAI 2021 · similarity 0.93)
- Toward Characteristic-Preserving Image-based Virtual Try-On Network (ECCV 2018 · similarity 0.92)
- Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks (ICCV 2025 · similarity 0.91)
- Virtual Try-On: Real-Time Interactive Hybrid Network with High-Fidelity (AAAI 2024 · similarity 0.91)
- CycleVTON: A Cycle Mapping Framework for Parser-Free Virtual Try-On (AAAI 2024 · similarity 0.89)
- IPVTON: Image-based 3D Virtual Try-on with Image Prompt Adapter (AAAI 2025 · similarity 0.88)
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.
