# Exposure: A White-Box Photo Post-Processing Framework

arXiv: https://arxiv.org/abs/1709.09602 · HTML: https://mlsanity.com/paper/1709.09602/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2017.

## Built on by (most cited first, 27 of 27)

- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [Invertible Image Signal Processing](https://mlsanity.com/paper/2103.15061/) (2021)
- [Types of Out-of-Distribution Texts and How to Detect Them](https://mlsanity.com/paper/2109.06827/) (2021)
- [Harmonizer: Learning to Perform White-Box Image and Video Harmonization](https://mlsanity.com/paper/2207.01322/) (2022)
- [Neural Preset for Color Style Transfer](https://mlsanity.com/paper/2303.13511/) (2023)
- [4D LUT: Learnable Context-Aware 4D Lookup Table for Image Enhancement](https://mlsanity.com/paper/2209.01749/) (2022)
- [ReconfigISP: Reconfigurable Camera Image Processing Pipeline](https://mlsanity.com/paper/2109.04760/) (2021)
- [ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement](https://mlsanity.com/paper/2107.05830/) (2021)
- [Learning by Planning: Language-Guided Global Image Editing](https://mlsanity.com/paper/2106.13156/) (2021)
- [Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement](https://mlsanity.com/paper/2112.05147/) (2021)
- [Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Model](https://mlsanity.com/paper/2306.07596/) (2023)
- [GDIP: Gated Differentiable Image Processing for Object-Detection in Adverse Conditions](https://mlsanity.com/paper/2209.14922/) (2022)
- [TSCnet: A Text-driven Semantic-level Controllable Framework for Customized Low-Light Image Enhancement](https://mlsanity.com/paper/2503.08168/) (2025)
- [WISE: Whitebox Image Stylization by Example-based Learning](https://mlsanity.com/paper/2207.14606/) (2022)
- [Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design](https://mlsanity.com/paper/2504.14075/) (2025)
- [DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning](https://mlsanity.com/paper/2207.03081/) (2022)
- [Holistic Dynamic Frequency Transformer for Image Fusion and Exposure Correction](https://mlsanity.com/paper/2309.01183/) (2023)
- [Tool- and Domain-Agnostic Parameterization of Style Transfer Effects Leveraging Pretrained Perceptual Metrics](https://mlsanity.com/paper/2105.09207/) (2021)
- [Deep Portrait Lighting Enhancement with 3D Guidance](https://mlsanity.com/paper/2108.02121/) (2021)
- [Reinforcement Learning of Self Enhancing Camera Image and Signal Processing](https://mlsanity.com/paper/2111.07499/) (2021)
- [TreEnhance: A Tree Search Method For Low-Light Image Enhancement](https://mlsanity.com/paper/2205.12639/) (2022)
- [Mutual Guidance and Residual Integration for Image Enhancement](https://mlsanity.com/paper/2211.13919/) (2022)
- [CURVE: CLIP-Utilized Reinforcement Learning for Visual Image Enhancement via Simple Image Processing](https://mlsanity.com/paper/2505.23102/) (2025)
- [Explaining Image Enhancement Black-Box Methods through a Path Planning Based Algorithm](https://mlsanity.com/paper/2207.07092/) (2022)
- [Reflectance-Guided, Contrast-Accumulated Histogram Equalization](https://mlsanity.com/paper/2209.06405/) (2022)
- [One-shot Detail Retouching with Patch Space Neural Transformation Blending](https://mlsanity.com/paper/2210.01217/) (2022)
- [Learning Camera-Agnostic White-Balance Preferences](https://mlsanity.com/paper/2507.01342/) (2025)

## Abstract (arXiv)

Retouching can significantly elevate the visual appeal of photos, but many casual photographers lack the expertise to do this well. To address this problem, previous works have proposed automatic retouching systems based on supervised learning from paired training images acquired before and after manual editing. As it is difficult for users to acquire paired images that reflect their retouching preferences, we present in this paper a deep learning approach that is instead trained on unpaired data, namely a set of photographs that exhibits a retouching style the user likes, which is much easier to collect. Our system is formulated using deep convolutional neural networks that learn to apply different retouching operations on an input image. Network training with respect to various types of edits is enabled by modeling these retouching operations in a unified manner as resolution-independent differentiable filters. To apply the filters in a proper sequence and with suitable parameters, we employ a deep reinforcement learning approach that learns to make decisions on what action to take next, given the current state of the image. In contrast to many deep learning systems, ours provides users with an understandable solution in the form of conventional retouching edits, rather than just a "black-box" result. Through quantitative comparisons and user studies, we show that this technique generates retouching results consistent with the provided photo set.