Goal Conditioned Reinforcement Learning for Photo Finishing Tuning
This addresses the slow and proxy-dependent tuning in photo editing software like Adobe Lightroom, offering a more efficient solution for users and developers, though it is incremental in improving existing automation methods.
The paper tackles the problem of automating photo finishing pipeline tuning by proposing a goal-conditioned reinforcement learning framework that treats the pipeline as a black box, achieving the desired parameters in just 10 queries compared to 200 for optimization-based methods.
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/.