Research map / Reinforcement learning / Visual and representation RL
RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes
Yuan-Kang Lee, Kuan-Lin Chen, Chia-Che Chang, Yu-Lun Liu
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 |
|---|---|---|---|
| add color filtering (ablation) | SGP-LRD · NCC | median angular error: 2.51 -> 2.12 | Improved |
| add color filtering (ablation) | SGP-LRD · LEVI | mean angular error: 3.68 -> 3.25 | Improved |
| add noise filtering (ablation) | SGP-LRD · NCC | median angular error: 2.12 -> 2.12 | No clear effect |
| add noise filtering (ablation) | SGP-LRD · NCC | worst-25% angular error: 7.32 -> 7.22 | Improved |
| use curriculum pool size 5 instead of 3 (ablation) | RL-AWB · NCC | median angular error: 2.16 -> 1.98 | Improved |
| use curriculum pool size 5 instead of 15 (ablation) | RL-AWB · NCC | median angular error: 2.24 -> 1.98 | Improved |
| use dual-branch backbone instead of single-branch (ablation) | RL-AWB · NCC | median angular error: 2.11 -> 1.98 | Improved |
| use SAC instead of PPO (ablation) | RL-AWB · NCC | median angular error: 2.16 -> 1.98 | Improved |
| use SAC instead of PPO (ablation) | RL-AWB · LEVI | median angular error: 3.09 -> 3.01 | Improved |
| add RL parameter tuning on top of SGP-LRD | SGP-LRD · NCC->LEVI | median angular error | Improved |
| replace one-step MLP regressor with RL agent | RL-AWB · NCC->NCC | median angular error: 2.01 -> 1.98 | Improved |
| add RL tuning to SGP-LRD | SGP-LRD · Gehler-Shi (trained on NCC) | median angular error: 2.38 -> 2.24 | Improved |
Closest papers by meaning
- NightCC: Nighttime Color Constancy via Adaptive Channel Masking (CVPR 2024 · similarity 0.87)
- White-Balance First, Adjust Later: Cross-Camera Color Constancy via Vision-Language Evaluation (CVPR 2026 · similarity 0.86)
- Learning to Control Camera Exposure via Reinforcement Learning (CVPR 2024 · similarity 0.85)
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (AAAI 2025 · similarity 0.84)
- Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing (CVPR 2024 · similarity 0.84)
- A Simple Framework for Generalization in Visual RL under Dynamic Scene Perturbations (NeurIPS 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.
