Research map / Graph learning / Knowledge and temporal graphs
GPS-Net: Graph-based Photometric Stereo Network
Read the paperCheck 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 |
|---|---|---|---|
| combine max and average in SGC filter output (vs max only) (ablation) | GPS-Net · DiLiGenT avg over input counts | MAE (degrees): 9.68 -> 9.34 | Helped |
| combine max and average in SGC filter output (vs average only) (ablation) | GPS-Net · DiLiGenT avg over input counts | MAE (degrees): 11.79 -> 9.34 | Helped |
| add average to max in SGC output at 96 inputs (ablation) | GPS-Net · DiLiGenT, 96 inputs | MAE (degrees): 7.92 -> 7.81 | Helped |
| multi-scale multi-branch NR-Net (IV) vs variant I (ablation) | GPS-Net NR-Net · DiLiGenT, 96 inputs | MAE (degrees): 9.39 -> 7.81 | Helped |
| too many 3x3 conv layers in NR-Net (variant II vs III) (ablation) | GPS-Net NR-Net · DiLiGenT, 96 inputs | MAE (degrees): 7.90 -> 8.38 | Hurt |
| UFE-Layer graph features replace observation map (vs CNN-PS) under sparse lighting | GPS-Net · DiLiGenT, 4 inputs | MAE (degrees): 47.82 -> 13.46 | Helped |
| GPS-Net vs CNN-PS under dense lighting | GPS-Net · DiLiGenT, 96 inputs | MAE (degrees): 7.21 -> 7.81 | Hurt |
| GPS-Net vs PS-FCN across input counts | GPS-Net · DiLiGenT avg | MAE (degrees): 10.33 -> 9.34 | Helped |
| GPS-Net vs PS-FCN on synthetic data with 100 inputs | GPS-Net · Synthetic sphere, 100 inputs | MAE (degrees): 3.96 -> 4.07 | Hurt |
Closest papers by meaning
- Universal Photometric Stereo Network Using Global Lighting Contexts (CVPR 2022 · similarity 0.90)
- Learning to Minify Photometric Stereo (CVPR 2019 · similarity 0.90)
- Scalable, Detailed and Mask-Free Universal Photometric Stereo (CVPR 2023 · similarity 0.89)
- Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces (CVPR 2021 · similarity 0.88)
- Light of Normals: Unified Feature Representation for Universal Photometric Stereo (ICLR 2026 · similarity 0.88)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 2024 · 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.