# Goal Conditioned Reinforcement Learning for Photo Finishing Tuning

arXiv: https://arxiv.org/abs/2503.07300 · HTML: https://mlsanity.com/paper/2503.07300/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in RL with diffusion and flow models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Placed in

- Deep reinforcement learning methods / [RL with diffusion and flow models](https://mlsanity.com/deeprl/rl-with-diffusion-and-flow-models/)

## Builds on (most cited first, 16 of 16)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [pymoo: Multi-objective Optimization in Python](https://mlsanity.com/paper/2002.04504/) (2020)
- [Replacing Mobile Camera ISP with a Single Deep Learning Model](https://mlsanity.com/paper/2002.05509/) (2020)
- [Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software](https://mlsanity.com/paper/1912.07833/) (2019)
- [Joint Bilateral Learning for Real-time Universal Photorealistic Style Transfer](https://mlsanity.com/paper/2004.10955/) (2020)
- [ReconfigISP: Reconfigurable Camera Image Processing Pipeline](https://mlsanity.com/paper/2109.04760/) (2021)
- [Automatic ISP image quality tuning using non-linear optimization](https://mlsanity.com/paper/1902.09023/) (2019)
- [Transform your Smartphone into a DSLR Camera: Learning the ISP in the Wild](https://mlsanity.com/paper/2203.10636/) (2022)
- [RAWtoBit: A Fully End-to-end Camera ISP Network](https://mlsanity.com/paper/2208.07639/) (2022)

## Built on by (most cited first, 6 of 6)

- [JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent](https://mlsanity.com/paper/2506.17612/) (2025)
- [Fine-grained Image Aesthetic Assessment: Learning Discriminative Scores from Relative Ranks](https://mlsanity.com/paper/2603.03907/) (2026)
- [RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models](https://mlsanity.com/paper/2510.08054/) (2025)
- [Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset](https://mlsanity.com/paper/2604.16114/) (2026)
- [Learning to Clean: Reinforcement Learning for Noisy Label Correction](https://mlsanity.com/paper/2511.19808/) (2025)
- [InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space](https://mlsanity.com/paper/2606.05071/) (2026)

## Abstract (arXiv)

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/.