Research map / 3D vision / Face and shape
Normal-Guided Garment UV Prediction for Human Re-Texturing
Yasamin Jafarian, Tuanfeng Y. Wang, Duygu Ceylan, Jimei Yang, Nathan Carr, Yi Zhou, Hyun Soo Park
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 |
|---|---|---|---|
| Use normal-guided isometry constraints for UV prediction | Garment UV prediction · GT dress sequences | UV error (cm): 5.56±0.29 -> 3.16±0.28 | Improved |
| Use normal-guided isometry constraints for UV prediction | Garment UV prediction · GT T-shirt sequences | UV error (cm): 5.75±0.20 -> 3.58±0.27 | Improved |
| Use normal-guided isometry constraints for UV prediction | Garment UV prediction · GT dress sequences | photometric error: 13.07±2.79 -> 7.54±2.04 | Improved |
| Use normal-guided isometry constraints for UV prediction | Garment UV prediction · GT T-shirt sequences | photometric error: 14.54±4.26 -> 11.28±2.01 | Improved |
| Add both distance and angle constraints rather than distance constraints alone (ablation) | Normal-guided garment UV prediction · GT dress sequences | UV error (cm): 3.44±0.25 -> 3.16±0.28 | Improved |
| Add distance constraints alongside the angle constraint (ablation) | Normal-guided garment UV prediction · GT dress sequences | UV error (cm): 5.96±0.33 -> 3.16±0.28 | Improved |
| Add temporal consistency loss L_tmp (ablation) | Video garment UV prediction · GT dress sequences | photometric error (RGB): 14.67±4.82 -> 7.54±2.04 | Improved |
| Add temporal consistency loss L_tmp (ablation) | Video garment UV prediction · GT dress sequences | UV error (cm): 3.22±0.24 -> 3.16±0.28 | No clear effect |
| Add proxy-map loss L_prox (ablation) | Normal-guided garment UV prediction · GT dress sequences | UV error (cm): 3.24±0.35 -> 3.16±0.28 | No clear effect |
| Add proxy-map loss L_prox (ablation) | Normal-guided garment UV prediction · GT dress sequences | photometric error (RGB): 8.46±2.19 -> 7.54±2.04 | Improved |
Closest papers by meaning
- Learning to Transfer Texture From Clothing Images to 3D Humans (CVPR 2020 · similarity 0.91)
- TexGarment: Consistent Garment UV Texture Generation via Efficient 3D Structure-Guided Diffusion Transformer (CVPR 2025 · similarity 0.89)
- Reconstruction of Manipulated Garment with Guided Deformation Prior (NeurIPS 2024 · similarity 0.89)
- Garment Recovery with Shape and Deformation Priors (CVPR 2024 · similarity 0.88)
- SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction (CVPR 2024 · similarity 0.87)
- DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images (NeurIPS 2026 · 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.
