用强化学习自动调图，10次查询就搞定，无需训练代理模型。
Goal Conditioned Reinforcement Learning for Photo Finishing Tuning
- 基于目标图像的强化学习框架，把调图当黑盒处理。
- 仅需10次查询即可找到最佳参数，远少于传统方法的200次。
- 支持图像、风格等视觉目标灵活调节，适合自动化调图场景。
照片后期调优旨在自动化 Adobe Lightroom 或 Darktable 等工具中的手动调参流程。以往方法或采用零阶优化，参数增多时速度慢；或依赖可微代理模型，但难以训练。为此，我们提出一种新的目标条件强化学习框架，利用目标图像作为条件，高效调参。与之前方法不同，本框架不依赖任何代理模型，将后期处理流程视为黑盒。通过训练好的强化学习策略，仅需10次查询即可找到理想参数组合，而传统优化方法通常需要200次。此外，该架构利用目标图像引导参数迭代调整，支持像素对齐的目标图像、风格图像或其他可视目标的灵活条件控制。我们在照片调优和风格化调优任务上进行了详尽实验，验证了该方法的优势。项目主页：https://openimaginglab.github.io/RLPixTuner/
原文摘要 · Abstract (English)
Photo finishing tuning aims to automate the manual tuning process of the photo finishing pipeline, like Adobe Lightroom or Darktable. Previous works either use zeroth-order optimization, which is slow when the set of parameters increases, or rely on a differentiable proxy of the target finishing pipeline, which is hard to train. To overcome these challenges, we propose a novel goal-conditioned reinforcement learning framework for efficiently tuning parameters using a goal image as a condition. Unlike previous approaches, our tuning framework does not rely on any proxy and treats the photo finishing pipeline as a black box. Utilizing a trained reinforcement learning policy, it can efficiently find the desired set of parameters within just 10 queries, while optimization based approaches normally take 200 queries. Furthermore, our architecture utilizes a goal image to guide the iterative tuning of pipeline parameters, allowing for flexible conditioning on pixel-aligned target images, style images, or any other visually representable goals. We conduct detailed experiments on photo finishing tuning and photo stylization tuning tasks, demonstrating the advantages of our method. Project website: https://openimaginglab.github.io/RLPixTuner/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。