Research map / 3D vision / Depth and stereo
Stereoscopic Flash and No-Flash Photography for Shape and Albedo Recovery
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 |
|---|---|---|---|
| Add confidence weighting for cast-shadow handling (ablation) | Stereoscopic Flash and No-Flash · Synthetic objects under PISA, DOGE, and GLACIER lighting | MAbsE: 3.43e-3 -> 3.39e-3; 2.42e-3 -> 2.48e-3; 3.54e-3 -> 3.44e-3; 3.09e-3 -> 2.98e-3; 3.45e-3 -> 3.41e-3; 3.69e-3 -> 3.64e-3 | Mixed |
| Use a flash/no-flash ratio image to cancel albedo variation during shape refinement | Stereoscopic Flash and No-Flash · Synthetic and real-world shape recovery | MAbsE: 3.43e-3 | Helped |
| Combine stereo-derived coarse shape with flash/no-flash shading constraints | Stereoscopic Flash and No-Flash · Shape and albedo recovery on synthetic and real-world data | shape detail recovery | Helped |
Closest papers by meaning
- SVBRDF-Invariant Shape and Reflectance Estimation From Light-Field Cameras (CVPR 2016 · similarity 0.88)
- Multi-View 3D Reconstruction of a Texture-Less Smooth Surface of Unknown Generic Reflectance (CVPR 2021 · similarity 0.86)
- De-Rendering the World's Revolutionary Artefacts (CVPR 2021 · similarity 0.86)
- Towards 3D Vision with Low-Cost Single-Photon Cameras (CVPR 2024 · similarity 0.84)
- 3D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction (NeurIPS 2025 · similarity 0.84)
- Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation (CVPR 2025 · 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.