English

Very Lightweight Photo Retouching Network with Conditional Sequential Modulation

Computer Vision and Pattern Recognition 2022-06-07 v2 Machine Learning

Abstract

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 1×11\times1 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.

Keywords

Cite

@article{arxiv.2104.06279,
  title  = {Very Lightweight Photo Retouching Network with Conditional Sequential Modulation},
  author = {Yihao Liu and Jingwen He and Xiangyu Chen and Zhengwen Zhang and Hengyuan Zhao and Chao Dong and Yu Qiao},
  journal= {arXiv preprint arXiv:2104.06279},
  year   = {2022}
}

Comments

Accepted by TMM. arXiv admin note: substantial text overlap with arXiv:2009.10390

R2 v1 2026-06-24T01:07:41.841Z