# Learning Diverse Tone Styles for Image Retouching arXiv: https://arxiv.org/abs/2207.05430 ยท HTML: https://mlsanity.com/paper/2207.05430/ ## Key facts - Cited by 8 papers in the map (data through 14 Oct 2026). - Builds on 30 of its 57 references that are in the map. - First posted on arXiv 12 Jul 2022. ## Builds on (most cited first, 30 of 30) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019) - [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018) - [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016) - [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019) - [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016) - [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018) - [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014) - [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017) - [StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows](https://mlsanity.com/paper/2008.02401/) (2020) - [SRFlow: Learning the Super-Resolution Space with Normalizing Flow](https://mlsanity.com/paper/2006.14200/) (2020) - [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017) - [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021) - [Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time](https://mlsanity.com/paper/2009.14468/) (2020) - [Guided Image Generation with Conditional Invertible Neural Networks](https://mlsanity.com/paper/1907.02392/) (2019) - [Noise Flow: Noise Modeling with Conditional Normalizing Flows](https://mlsanity.com/paper/1908.08453/) (2019) - [DeepLPF: Deep Local Parametric Filters for Image Enhancement](https://mlsanity.com/paper/2003.13985/) (2020) - [Flow-based Kernel Prior with Application to Blind Super-Resolution](https://mlsanity.com/paper/2103.15977/) (2021) - [Conditional Sequential Modulation for Efficient Global Image Retouching](https://mlsanity.com/paper/2009.10390/) (2020) - [PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency](https://mlsanity.com/paper/2105.09180/) (2021) - [Distort-and-Recover: Color Enhancement using Deep Reinforcement Learning](https://mlsanity.com/paper/1804.04450/) (2018) - [Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network](https://mlsanity.com/paper/2012.15020/) (2020) - [Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software](https://mlsanity.com/paper/1912.07833/) (2019) - [StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement](https://mlsanity.com/paper/2107.12898/) (2021) - [Noise Conditional Flow Model for Learning the Super-Resolution Space](https://mlsanity.com/paper/2106.04428/) (2021) - [Flexible Piecewise Curves Estimation for Photo Enhancement](https://mlsanity.com/paper/2010.13412/) (2020) - [Unpaired Learning for High Dynamic Range Image Tone Mapping](https://mlsanity.com/paper/2111.00219/) (2021) - [Unpaired Image Enhancement with Quality-Attention Generative Adversarial Network](https://mlsanity.com/paper/2012.15052/) (2020) - [Perceptually Optimized Deep High-Dynamic-Range Image Tone Mapping](https://mlsanity.com/paper/2109.00180/) (2021) ## Built on by (most cited first, 8 of 8) - [CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models](https://mlsanity.com/paper/2404.15677/) (2024) - [DiffRetouch: Using Diffusion to Retouch on the Shoulder of Experts](https://mlsanity.com/paper/2407.03757/) (2024) - [PhotoArtAgent: Intelligent Photo Retouching with Language Model-Based Artist Agents](https://mlsanity.com/paper/2505.23130/) (2025) - [On the Robustness of Normalizing Flows for Inverse Problems in Imaging](https://mlsanity.com/paper/2212.04319/) (2022) - [Learning Adaptive Lighting via Channel-Aware Guidance](https://mlsanity.com/paper/2412.01493/) (2024) - [RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models](https://mlsanity.com/paper/2510.08054/) (2025) - [Brighten-and-Colorize: A Decoupled Network for Customized Low-Light Image Enhancement](https://mlsanity.com/paper/2308.03029/) (2023) - [Content-Adaptive Image Retouching Guided by Attribute-Based Text Representation](https://mlsanity.com/paper/2512.09580/) (2025) ## Abstract (arXiv) Image retouching, aiming to regenerate the visually pleasing renditions of given images, is a subjective task where the users are with different aesthetic sensations. Most existing methods deploy a deterministic model to learn the retouching style from a specific expert, making it less flexible to meet diverse subjective preferences. Besides, the intrinsic diversity of an expert due to the targeted processing on different images is also deficiently described. To circumvent such issues, we propose to learn diverse image retouching with normalizing flow-based architectures. Unlike current flow-based methods which directly generate the output image, we argue that learning in a style domain could (i) disentangle the retouching styles from the image content, (ii) lead to a stable style presentation form, and (iii) avoid the spatial disharmony effects. For obtaining meaningful image tone style representations, a joint-training pipeline is delicately designed, which is composed of a style encoder, a conditional RetouchNet, and the image tone style normalizing flow (TSFlow) module. In particular, the style encoder predicts the target style representation of an input image, which serves as the conditional information in the RetouchNet for retouching, while the TSFlow maps the style representation vector into a Gaussian distribution in the forward pass. After training, the TSFlow can generate diverse image tone style vectors by sampling from the Gaussian distribution. Extensive experiments on MIT-Adobe FiveK and PPR10K datasets show that our proposed method performs favorably against state-of-the-art methods and is effective in generating diverse results to satisfy different human aesthetic preferences. Source code and pre-trained models are publicly available at https://github.com/SSRHeart/TSFlow.