Research map / Learning theory and algorithms / Sample complexity
Fast Fourier Color Constancy
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 |
|---|---|---|---|
| Replace CCC with FFCC Model J | Color constancy on Gehler-Shi · Gehler-Shi | average angular error: 1.40 -> 1.20 | Helped |
| Add metadata and semantic features (ablation) | FFCC Model J · Gehler-Shi | average angular error: 1.20 -> 1.07 | Helped |
| Add metadata (ablation) | FFCC Model J · Gehler-Shi | average angular error: 1.20 -> 1.10 | Helped |
| Add semantic features (ablation) | FFCC Model J · Gehler-Shi | average angular error: 1.20 -> 1.15 | Helped |
| Remove frequency-domain preconditioning (ablation) | FFCC Model J · Gehler-Shi | average angular error: 1.20 -> 2.18 | Hurt |
| Remove total variation regularization (ablation) | FFCC Model J · Gehler-Shi | average angular error: 1.20 -> 1.30 | Hurt |
| Remove BVM loss (ablation) | FFCC Model J · Gehler-Shi | average angular error: 1.20 -> 1.78 | Hurt |
| Remove illuminant gain and bias maps (ablation) | FFCC Model J · Gehler-Shi | average angular error: 1.20 -> 1.53 | Hurt |
| Remove regularization (ablation) | FFCC Model J · Gehler-Shi | average angular error: 1.20 -> 1.70 | Hurt |
| Use gray-world rather than gray-light de-aliasing (ablation) | FFCC Model J · Gehler-Shi | average angular error: 1.20 -> 1.24 | Hurt |
| Use 4 channels instead of 2 (ablation) | FFCC · Gehler-Shi | average angular error: 1.20 -> 1.21 | No clear effect |
| Use thumbnail input rather than full input (ablation) | FFCC · Gehler-Shi | average angular error: 1.20 -> 1.37 | Hurt |
Closest papers by meaning
- Integral Fast Fourier Color Constancy (CVPR 2025 · similarity 0.90)
- GCC: Generative Color Constancy via Diffusing a Color Checker (CVPR 2025 · similarity 0.86)
- Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing (CVPR 2024 · similarity 0.84)
- LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation (CVPR 2024 · similarity 0.83)
- NightCC: Nighttime Color Constancy via Adaptive Channel Masking (CVPR 2024 · similarity 0.83)
- Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring (CVPR 2024 · similarity 0.82)
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.