Research map / 3D vision / Face and shape
3D Human Shape Reconstruction from a Polarization Image
Shihao Zou, Xinxin Zuo, Yiming Qian, Sen Wang, Chi Xu, Minglun Gong, Li Cheng
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 |
|---|---|---|---|
| add physical priors (ambiguous normal maps) (ablation) | SfP normal estimation · PHSPD normal estimation | MAE: 24.71 -> 20.75 | Improved |
| add physical priors (ambiguous normal maps) (ablation) | SfP normal estimation · SURREAL normal estimation | MAE: 13.89 -> 7.10 | Improved |
| add fused normal maps (ablation) | SfP normal estimation · PHSPD normal estimation | MAE: 21.65 -> 20.75 | Improved |
| add fused normal maps (ablation) | SfP normal estimation · SURREAL normal estimation | MAE: 7.43 -> 7.10 | Improved |
| use polarization image instead of color image (ablation) | SfP normal estimation · SURREAL normal estimation | MAE: 19.49 -> 7.10 | Improved |
| add estimated normal map for pose, polarization input (ablation) | SfP · SURREAL | MPJPE 20 joints (mm): 83.43 -> 67.25 | Improved |
| add estimated normal map for pose, polarization input (ablation) | SfP · PHSPD | MPJPE 20 joints (mm): 84.44 -> 66.32 | Improved |
| add estimated normal map for pose, color input (ablation) | SfP · SURREAL | MPJPE 20 joints (mm): 88.53 -> 80.70 | Improved |
| add estimated normal map for pose, color input (ablation) | SfP · PHSPD | MPJPE 20 joints (mm): 85.67 -> 77.72 | Improved |
| add deformation step to shape recovery (ablation) | SfP · PHSPD clothed shape | 3D surface error (mm): 41.10 -> 38.92 | Improved |
| use polarization image instead of color image (HMR baseline) (ablation) | HMR · PHSPD (GT-t) | MPJPE 20 joints (mm): 82.96 -> 77.57 | Improved |
Closest papers by meaning
- Deep Shape from Polarization (ECCV 2020 · similarity 0.88)
- Shape From Polarization for Complex Scenes in the Wild (CVPR 2022 · similarity 0.88)
- Learning Accurate 3D Shape Based on Stereo Polarimetric Imaging (CVPR 2023 · similarity 0.88)
- 3DPeople: Modeling the Geometry of Dressed Humans (ICCV 2019 · similarity 0.88)
- Deep Polarization Imaging for 3D Shape and SVBRDF Acquisition (CVPR 2021 · similarity 0.88)
- MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction (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.
