Research map / 3D vision / Face and shape
Toward a Universal Model for Shape From Texture
Dor Verbin, Todd Zickler
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 |
|---|---|---|---|
| Compare against stationarity-based shape from texture on texture 1 | Three-player game · Synthetic textures | MAE (degrees): 30.5 -> 15.2 | Improved |
| Compare against isolated-texton method [16] on texture 5 | Three-player game · Synthetic textures | MAE (degrees): 41.7 -> 18.6 | Improved |
| Compare against isolated-texton method [17] on texture 3 | Three-player game · Synthetic textures | MAE (degrees): 12.9 -> 12.6 | No clear effect |
| Compare against isolated-texton method [17] on texture 11 (well-separated textons) | Three-player game · Synthetic textures | MAE (degrees): 6.9 -> 14.9 | Hurt |
| Compare against [16] on texture 10 | Three-player game · Synthetic textures | MAE (degrees): 47.6 -> 20.1 | Improved |
| Compare against [16] on texture 8 | Three-player game · Synthetic textures | MAE (degrees): 17.6 -> 17.1 | No clear effect |
| Compare against [16] on texture 11 | Three-player game · Synthetic textures | MAE (degrees): 9.2 -> 14.9 | Hurt |
| Add shading, gloss and clutter to rendered scene | Three-player game · Synthetic sphere | shape accuracy | No clear effect |
| Increase texture scale beyond the largest unwarper patch size | Three-player game · Synthetic sphere | shape accuracy | Hurt |
| Use a Gaussian pyramid for tangent vectors (ablation) | Three-player game · Shape parametrization | shape quality | No clear effect |
| Add local maps earlier in the generator rather than later (ablation) | Generator · Real images | shape accuracy | Hurt |
| Remove Gaussian pyramid for normals (multiscale) (ablation) | Normal parametrization · Shape recovery | shape quality | Improved |
Closest papers by meaning
- Visual Anagrams Reveal Hidden Differences in Holistic Shape Processing Across Vision Models (NeurIPS 2025 · similarity 0.87)
- Multistable Shape from Shading Emerges from Patch Diffusion (NeurIPS 2024 · similarity 0.86)
- TextureDreamer: Image-Guided Texture Synthesis Through Geometry-Aware Diffusion (CVPR 2024 · similarity 0.86)
- Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape (ICLR 2024 · similarity 0.85)
- Generative Perception of Shape and Material from Differential Motion (NeurIPS 2025 · similarity 0.85)
- Wukong's 72 Transformations: High-fidelity Textured 3D Morphing via Flow Models (NeurIPS 2025 · similarity 0.85)
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.
