Research map / 3D vision / Face and shape
AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesis
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 color loss L_c (ablation) | AUV-Net · ShapeNet cars | IOU: 68.5 -> 72.7 | Helped |
| Add color loss L_c (ablation) | AUV-Net · ShapeNet chairs | IOU: 85.2 -> 85.8 | No clear effect |
| Add normal loss L_n (ablation) | AUV-Net · ShapeNet cars and chairs | IOU: Cars: 71.7 -> 72.7; chairs: 84.6 -> 85.8 | Helped |
| Add cycle loss L_x (ablation) | AUV-Net · ShapeNet cars and chairs | IOU: Cars: 73.0 -> 72.7; chairs: 83.7 -> 85.8 | Mixed |
| Add smoothness loss L_s (ablation) | AUV-Net · ShapeNet cars and chairs | IOU: Cars: 72.8 -> 72.7; chairs: 87.1 -> 85.8 | Mixed |
| Add prior loss L_p (ablation) | AUV-Net · ShapeNet cars and chairs | IOU: Cars: 70.6 -> 72.7; chairs: 85.7 -> 85.8 | Helped |
| Add masker (ablation) | AUV-Net · ShapeNet cars and chairs | IOU: Cars: 72.0 -> 72.7; chairs: 71.1 -> 85.8 | Helped |
| Use aligned texture maps for texture generation instead of Texture Fields | Texture synthesis · Triplegangers heads | FID: 24.59 -> 5.69 | Helped |
| Use aligned texture maps for texture generation instead of Texture Fields | Texture synthesis · ShapeNet cars and chairs | FID: Cars: 53.09 -> 12.11; chairs: 7.03 -> 5.33 | Helped |
| Use AUV-Net rather than Texture Fields for textured single-view reconstruction | Textured single-view reconstruction · ShapeNet cars and chairs | FID: Cars: 92.89 -> 40.85; chairs: 36.89 -> 33.26 | Helped |
| Use AUV-Net rather than Texture Fields for textured single-view reconstruction | Textured single-view reconstruction · ShapeNet cars and chairs | SSIM: Cars: 0.897 -> 0.894; chairs: 0.855 -> 0.853 | Hurt |
| Use AUV-Net rather than Texture Fields for textured single-view reconstruction | Textured single-view reconstruction · ShapeNet cars and chairs | feature-l1: Cars: 0.219 -> 0.186; chairs: 0.193 -> 0.189 | Helped |
Closest papers by meaning
- TUVF: Learning Generalizable Texture UV Radiance Fields (ICLR 2024 · similarity 0.90)
- TriTex: Learning Texture from a Single Mesh via Triplane Semantic Features (CVPR 2025 · similarity 0.87)
- Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models (CVPR 2024 · similarity 0.87)
- TextureDreamer: Image-Guided Texture Synthesis Through Geometry-Aware Diffusion (CVPR 2024 · similarity 0.87)
- Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering (CVPR 2024 · similarity 0.87)
- SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement (CVPR 2025 · similarity 0.86)
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.