Research map / 3D vision / Face and shape
Shape and Material Capture at Home
Daniel Lichy, Jiaye Wu, Soumyadip Sengupta, David W. Jacobs
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 |
|---|---|---|---|
| use recursive multi-resolution RecNet instead of a same-resolution ResNet (ablation) | Shape and Material Capture at Home · DiLiGenT, 3 images | MAE (degrees): 14.8 -> 12.5 | Improved |
| use recursive multi-resolution RecNet instead of a same-resolution ResNet (ablation) | Shape and Material Capture at Home · DiLiGenT, 1 image | MAE (degrees): 19.1 -> 16.7 | Improved |
| train separate fixed-input-count networks instead of one network for varying input counts (ablation) | Shape and Material Capture at Home · DiLiGenT, 3 images | MAE (degrees): 12.5 -> 10.7 | Improved |
| train separate fixed-input-count networks instead of one network for varying input counts (ablation) | Shape and Material Capture at Home · DiLiGenT, 1 image | MAE (degrees): 16.7 -> 16.1 | Improved |
| increase lighting-direction deviation from 4.8° to 12.2° (ablation) | Shape and Material Capture at Home · DiLiGenT | MAE: 12.5 -> 12.7 | No clear effect |
| increase lighting-direction deviation from 12.2° to 21.6° (ablation) | Shape and Material Capture at Home · DiLiGenT | MAE: 12.7 -> 15.0 | Hurt |
| increase intensity scaling standard deviation from 0 to 0.2 (ablation) | Shape and Material Capture at Home · DiLiGenT | MAE: 12.5 -> 12.5 | No clear effect |
| increase intensity scaling standard deviation from 0.2 to 1.2 (ablation) | Shape and Material Capture at Home · DiLiGenT | MAE: 12.5 -> 16.2 | Hurt |
Closest papers by meaning
- Reflectance and Natural Illumination from Single-Material Specular Objects Using Deep Learning (TPAMI 2017 · similarity 0.90)
- Neural Reflectance for Shape Recovery With Shadow Handling (CVPR 2022 · similarity 0.90)
- Shape and Reflectance Estimation in the Wild (TPAMI 2016 · similarity 0.89)
- Differentiable Neural Surface Refinement for Modeling Transparent Objects (CVPR 2024 · similarity 0.87)
- Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective Scenes (AAAI 2025 · similarity 0.86)
- Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion (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.
