← Back to Papers
Key Insights
- Introduces a hybrid pipeline that first applies a bespoke statistical gray‑pixel detector to estimate illumination in noisy, low‑light scenes.
- Develops the first deep reinforcement learning (DRL) agent that treats the statistical estimator as its environment, learning to fine‑tune AWB parameters per‑image in a manner akin to a human expert.
- The DRL policy dynamically adjusts gains, offsets, and color correction matrices, achieving superior accuracy compared with purely model‑based or purely learning‑based baselines.
- Releases a multi‑sensor nighttime dataset, enabling cross‑camera evaluation and demonstrating that the learned policy generalizes to both extreme low‑light and well‑illuminated images.
Abstract
Nighttimecolor constancyremains a challenging problem in computational photography due to low-light noise and complex illumination conditions. We present RL-AWB, a novel framework combining statistical methods withdeep reinforcement learningfor nighttimewhite balance. Our method begins with a statistical algorithm tailored for nighttime scenes, integrating salient gray pixel detection with novelillumination estimation. Building on this foundation, we develop the firstdeep reinforcement learningapproach forcolor constancythat leverages the statistical algorithm as its core, mimicking professional AWB tuning experts by dynamically optimizing parameters for each image. To facilitate cross-sensor evaluation, we introduce the first multi-sensor nighttime dataset. Experiment results demonstrate that our method achieves superior generalization capability across low-light and well-illuminated images. Project page: https://ntuneillee.github.io/research/rl-awb/
Full Analysis
# RL‑AWB: Reinforcement Learning for Nighttime White Balance
**Authors:** Yuan-Kang Lee,
**Source:** [HuggingFace](https://huggingface.co/papers/2601.05249) | [arXiv](https://arxiv.org/abs/2601.05249)
**Published:** 2026-01-09
**Organization:** Hugging Face
## Summary
- Introduces a hybrid pipeline that first applies a bespoke statistical gray‑pixel detector to estimate illumination in noisy, low‑light scenes.
- Develops the first deep reinforcement learning (DRL) agent that treats the statistical estimator as its environment, learning to fine‑tune AWB parameters per‑image in a manner akin to a human expert.
- The DRL policy dynamically adjusts gains, offsets, and color correction matrices, achieving superior accuracy compared with purely model‑based or purely learning‑based baselines.
- Releases a multi‑sensor nighttime dataset, enabling cross‑camera evaluation and demonstrating that the learned policy generalizes to both extreme low‑light and well‑illuminated images.
## Abstract
Nighttimecolor constancyremains a challenging problem in computational photography due to low-light noise and complex illumination conditions. We present RL-AWB, a novel framework combining statistical methods withdeep reinforcement learningfor nighttimewhite balance. Our method begins with a statistical algorithm tailored for nighttime scenes, integrating salient gray pixel detection with novelillumination estimation. Building on this foundation, we develop the firstdeep reinforcement learningapproach forcolor constancythat leverages the statistical algorithm as its core, mimicking professional AWB tuning experts by dynamically optimizing parameters for each image. To facilitate cross-sensor evaluation, we introduce the first multi-sensor nighttime dataset. Experiment results demonstrate that our method achieves superior generalization capability across low-light and well-illuminated images. Project page: https://ntuneillee.github.io/research/rl-awb/
---
*Topics: reinforcement-learning, computer-vision*
*Difficulty: advanced*
*Upvotes: 19*