# Very Lightweight Photo Retouching Network with Conditional Sequential Modulation

arXiv: https://arxiv.org/abs/2104.06279 · HTML: https://mlsanity.com/paper/2104.06279/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 61 references that are in the map.
- First posted on arXiv 13 Apr 2021.

## Builds on (most cited first, 28 of 28)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time](https://mlsanity.com/paper/2009.14468/) (2020)
- [DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks](https://mlsanity.com/paper/1704.02470/) (2017)
- [RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution](https://mlsanity.com/paper/1908.06382/) (2019)
- [FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazing](https://mlsanity.com/paper/2001.06968/) (2020)
- [Conditional Sequential Modulation for Efficient Global Image Retouching](https://mlsanity.com/paper/2009.10390/) (2020)
- [Distort-and-Recover: Color Enhancement using Deep Reinforcement Learning](https://mlsanity.com/paper/1804.04450/) (2018)
- [Deep Network Interpolation for Continuous Imagery Effect Transition](https://mlsanity.com/paper/1811.10515/) (2018)
- [Fast Image Processing with Fully-Convolutional Networks](https://mlsanity.com/paper/1709.00643/) (2017)
- [Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers](https://mlsanity.com/paper/1904.08118/) (2019)
- [Aesthetic-Driven Image Enhancement by Adversarial Learning](https://mlsanity.com/paper/1707.05251/) (2017)
- [Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software](https://mlsanity.com/paper/1912.07833/) (2019)
- [WESPE: Weakly Supervised Photo Enhancer for Digital Cameras](https://mlsanity.com/paper/1709.01118/) (2017)
- [Supervised and Unsupervised Learning of Parameterized Color Enhancement](https://mlsanity.com/paper/2001.05843/) (2019)
- [Unpaired Image Enhancement with Quality-Attention Generative Adversarial Network](https://mlsanity.com/paper/2012.15052/) (2020)
- [Dynamic-Net: Tuning the Objective Without Re-training for Synthesis Tasks](https://mlsanity.com/paper/1811.08760/) (2018)
- [Automatic Content-Aware Color and Tone Stylization](https://mlsanity.com/paper/1511.03748/) (2015)
- [Enhancing Underexposed Photos using Perceptually Bidirectional Similarity](https://mlsanity.com/paper/1907.10992/) (2019)

## Built on by (most cited first, 14 of 14)

- [HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization](https://mlsanity.com/paper/2105.13084/) (2021)
- [4D LUT: Learnable Context-Aware 4D Lookup Table for Image Enhancement](https://mlsanity.com/paper/2209.01749/) (2022)
- [A New Journey from SDRTV to HDRTV](https://mlsanity.com/paper/2108.07978/) (2021)
- [Unifying Image Processing as Visual Prompting Question Answering](https://mlsanity.com/paper/2310.10513/) (2023)
- [MonetGPT: Solving Puzzles Enhances MLLMs' Image Retouching Skills](https://mlsanity.com/paper/2505.06176/) (2025)
- [CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigm](https://mlsanity.com/paper/2207.05359/) (2022)
- [Neural Color Operators for Sequential Image Retouching](https://mlsanity.com/paper/2207.08080/) (2022)
- [Learning to See Low-Light Images via Feature Domain Adaptation](https://mlsanity.com/paper/2312.06723/) (2023)
- [AdaCM: Adaptive ColorMLP for Real-Time Universal Photo-realistic Style Transfer](https://mlsanity.com/paper/2212.01567/) (2022)
- [LHDR: HDR Reconstruction for Legacy Content using a Lightweight DNN](https://mlsanity.com/paper/2211.11270/) (2022)
- [Towards Efficient SDRTV-to-HDRTV by Learning from Image Formation](https://mlsanity.com/paper/2309.04084/) (2023)
- [Efficient HDR Reconstruction from Real-World Raw Images](https://mlsanity.com/paper/2306.10311/) (2023)
- [Simplifying Low-Light Image Enhancement Networks with Relative Loss Functions](https://mlsanity.com/paper/2304.02978/) (2023)
- [TGTM: TinyML-based Global Tone Mapping for HDR Sensors](https://mlsanity.com/paper/2405.05016/) (2024)

## Abstract (arXiv)

Photo retouching aims at improving the aesthetic visual quality of images that suffer from photographic defects, especially for poor contrast, over/under exposure, and inharmonious saturation. In practice, photo retouching can be accomplished by a series of image processing operations. As most commonly-used retouching operations are pixel-independent, i.e., the manipulation on one pixel is uncorrelated with its neighboring pixels, we can take advantage of this property and design a specialized algorithm for efficient global photo retouching. We analyze these global operations and find that they can be mathematically formulated by a Multi-Layer Perceptron (MLP). Based on this observation, we propose an extremely lightweight framework -- Conditional Sequential Retouching Network (CSRNet). Benefiting from the utilization of 1×1 convolution, CSRNet only contains less than 37K trainable parameters, which are orders of magnitude smaller than existing learning-based methods. Experiments show that our method achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively. In addition to achieve global photo retouching, the proposed framework can be easily extended to learn local enhancement effects. The extended model, namely CSRNet-L, also achieves competitive results in various local enhancement tasks. Codes are available at https://github.com/lyh-18/CSRNet.