Research map / 3D vision / Depth and stereo
Light Source Separation and Intrinsic Image Decomposition Under AC Illumination
Yusaku Yoshida, Ryo Kawahara, Takahiro Okabe
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 |
|---|---|---|---|
| Resolve the blind LSS factorization ambiguity by integrating LSS with diffuse IID | LSS via NMF · Synthetic and real image sequences under AC illumination | PSNR | Improved |
| Resolve diffuse IID color ambiguity using specular highlights and the dichromatic reflection model (ablation) | Diffuse IID · Synthetic scenes (i–iv), light source colors | light source color: (0.33, 0.33, 0.33) -> (0.42, 0.37, 0.21); (0.33, 0.33, 0.33) -> (0.41, 0.38, 0.21); (0.33, 0.33, 0.33) -> (0.42, 0.36, 0 | Improved |
| Resolve diffuse IID color ambiguity using specular highlights and the dichromatic reflection model (ablation) | Diffuse IID · Synthetic scenes (i–iv), light source colors | light source color: (0.28, 0.16, 0.56) -> (0.39, 0.20, 0.41); (0.28, 0.16, 0.57) -> (0.38, 0.20, 0.43); (0.28, 0.17, 0.56) -> (0.39, 0.20, 0 | Improved |
| Resolve diffuse IID color ambiguity using specular highlights and the dichromatic reflection model (ablation) | Diffuse IID · Real scenes (A–B), light source colors | light source color: (0.33, 0.33, 0.33) -> (0.58, 0.29, 0.13); (0.33, 0.33, 0.33) -> (0.57, 0.28, 0.15) | Improved |
| Resolve diffuse IID color ambiguity using specular highlights and the dichromatic reflection model (ablation) | Diffuse IID · Real scenes (A–B), light source colors | light source color: (0.16, 0.39, 0.45) -> (0.24, 0.33, 0.44); (0.16, 0.39, 0.45) -> (0.20, 0.38, 0.42) | Improved |
Closest papers by meaning
- Latent Intrinsics Emerge from Training to Relight (NeurIPS 2024 · similarity 0.85)
- Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects (CVPR 2025 · similarity 0.84)
- Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing (CVPR 2024 · similarity 0.84)
- ESR-NeRF: Emissive Source Reconstruction Using LDR Multi-view Images (CVPR 2024 · similarity 0.83)
- IllumiNeRF: 3D Relighting Without Inverse Rendering (NeurIPS 2024 · similarity 0.83)
- RobIR: Robust Inverse Rendering for High-Illumination Scenes (NeurIPS 2024 · similarity 0.83)
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.
