Research map / Image generation / Image restoration
Reflective and Fluorescent Separation Under Narrow-Band Illumination
Koji Koyamatsu, Daichi Hidaka, Takahiro Okabe, Hendrik P. A. Lensch
Check 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 |
|---|---|---|---|
| Replace the channel-wise ICA model with the pixel-wise intersection model (ablation) | Reflective-fluorescent separation · Synthetic first object, σw=10, σn=2 | RMS error: 38.4 -> 5.1 | Improved |
| Add a fluorescent-color prior to intersection-based estimation (ablation) | Reflective-fluorescent separation · Synthetic second object, σw=10, σn=2 | RMS error: 12.7 -> 6.8 | Improved |
| Use one input image rather than multiple images with MAP estimation (ablation) | MAP separation · Synthetic first object, σw=10, σn=2 | RMS error: 4.7 -> 8.7 | Hurt |
| Use one input image rather than multiple images with MAP estimation (ablation) | MAP separation · Synthetic second object, σw=10, σn=2 | RMS error: 6.8 -> 5.6 | Improved |
| Use the MAP prior instead of the intersection method alone (ablation) | Reflective-fluorescent separation · Synthetic images, especially when light-source colors are similar or noise increases | RMS error: 12.7 -> 6.8 | Improved |
| Use the MAP prior instead of the intersection method alone (ablation) | Reflective-fluorescent separation · Real images | dot product: 0.982 -> 0.983; 0.989 -> 0.991; 0.996 -> 0.999; 0.996 -> 0.998 | Mixed |
| Use MAP estimation from one image rather than multiple images (ablation) | Reflective-fluorescent separation · Real images | dot product: 0.983 -> 0.983; 0.991 -> 0.992; 0.999 -> 0.999; 0.998 -> 0.998 | No clear effect |
| Use MAP estimation from one image rather than multiple images (ablation) | Reflective-fluorescent separation · When light-source colors are similar to fluorescent colors | separation quality | Hurt |
Closest papers by meaning
- Reflectance and Fluorescence Spectral Recovery via Actively Lit RGB Images (TPAMI 2016 · similarity 0.89)
- Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectance (CVPR 2024 · similarity 0.84)
- PolarFree: Polarization-based Reflection-Free Imaging (CVPR 2025 · similarity 0.83)
- RGB-to-Polarization Estimation: A New Task and Benchmark Study (NeurIPS 2025 · similarity 0.83)
- Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects (CVPR 2025 · similarity 0.83)
- GCC: Generative Color Constancy via Diffusing a Color Checker (CVPR 2025 · 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.
