Research map / 3D vision / Depth and stereo
Fast Light-Weight Near-Field Photometric Stereo
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 |
|---|---|---|---|
| Use the recursive near-field method instead of L20 | Near-field photometric stereo · LUCES calibrated | MAE: 13.33 -> 11.32 | Helped |
| Use the recursive near-field method instead of S20 | Near-field photometric stereo · LUCES uncalibrated | MAE: 16.03 -> 14.11 | Helped |
| Add optimization-based normal-integration post-processing | Ours · LUCES calibrated | MZE: 4.43 -> 2.93 | Helped |
| Add optimization-based normal-integration post-processing | Ours · LUCES uncalibrated | MZE: 4.71 -> 3.93 | Helped |
| Use recursive inference instead of L20 | Near-field photometric stereo · LUCES calibrated, resolution 512 | inference time (s): 59.5 -> 1.3 | Helped |
| Add per-pixel lighting estimation as input to the normal network (ablation) | Ours · LUCES calibrated | MAE: 14.88 -> 11.32 | Helped |
| Add per-pixel lighting estimation as input to the normal network (ablation) | Ours · LUCES calibrated | MZE: 4.89 -> 4.43 | Helped |
Closest papers by meaning
- Semi-Calibrated Near Field Photometric Stereo (CVPR 2017 · similarity 0.90)
- Sparse Views Near Light: A Practical Paradigm for Uncalibrated Point-light Photometric Stereo (CVPR 2024 · similarity 0.89)
- Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces (CVPR 2021 · similarity 0.88)
- Uncertainty-Aware Deep Multi-View Photometric Stereo (CVPR 2022 · similarity 0.88)
- RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction (CVPR 2024 · similarity 0.86)
- 3D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction (NeurIPS 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.