Research map / 3D vision / Depth and stereo
A Unified Spatial-Angular Structured Light for Single-View Acquisition of Shape and Reflectance
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 |
|---|---|---|---|
| Use the unified spatial-angular structured light for joint shape and reflectance acquisition | Single-view object capture · Shape and reflectance capture | geometric accuracy and reflectance SSIM: 0.27mm(mean distance); 0.94(SSIM) | Helped |
| Use the proposed depth acquisition instead of MPS | Shape capture · Shape capture, Fig. 5 sample 1 | accuracy (A): 0.72 -> 0.88 | Helped |
| Use the proposed reflectance reconstruction instead of Light Cube | Reflectance capture · Reflectance capture, Fig. 7 | SSIM: 0.89 -> 0.91 | Helped |
| Increase mask patterns from 12 to 18 (ablation) | Proposed depth acquisition · Shape capture, Fig. 8 | accuracy (A): 0.78 -> 0.80 | Helped |
| Increase mask patterns from 18 to 24 (ablation) | Proposed depth acquisition · Shape capture, Fig. 8 | accuracy (A): 0.80 -> 0.84 | Helped |
| Increase the number of LEDs from 1 to 4 (ablation) | Proposed depth acquisition · Shape capture, Fig. 9 | accuracy (A): 0.52 -> 0.62 | Helped |
| Increase the number of LEDs from 4 to 9 (ablation) | Proposed depth acquisition · Shape capture, Fig. 9 | accuracy (A): 0.62 -> 0.66 | Helped |
| Use optimized mask patterns instead of MPS patterns (ablation) | Depth reconstruction pipeline · Shape capture, Fig. 10 | accuracy (A): 0.71 -> 0.79 | Helped |
| Use optimized mask patterns instead of Gray code patterns (ablation) | Depth reconstruction pipeline · Shape capture, Fig. 10 | accuracy (A): 0.72 -> 0.79 | Helped |
| Use optimized light patterns instead of random point-light patterns (ablation) | Reflectance capture · Reflectance capture, Fig. 11 | SSIM: 0.95 -> 0.96 | Helped |
| Increase optimized light patterns from 32 to 48 (ablation) | Reflectance capture · Reflectance capture, Fig. 11 | SSIM: 0.96 -> 0.96 | No clear effect |
| Fine-tune reflectance by optimizing against measured light-pattern responses instead of relying on network inference | Reflectance reconstruction · Reflectance capture | SSIM | Helped |
Closest papers by meaning
- Real-time Acquisition and Reconstruction of Dynamic Volumes with Neural Structured Illumination (CVPR 2024 · similarity 0.85)
- TurboSL: Dense Accurate and Fast 3D by Neural Inverse Structured Light (CVPR 2024 · similarity 0.85)
- Sparse Views Near Light: A Practical Paradigm for Uncalibrated Point-light Photometric Stereo (CVPR 2024 · similarity 0.85)
- Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects (CVPR 2025 · similarity 0.84)
- SpecNeRF: Gaussian Directional Encoding for Specular Reflections (CVPR 2024 · similarity 0.84)
- Differentiable Display Photometric Stereo (CVPR 2024 · similarity 0.84)
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.