Conditional Sequential Modulation for Efficient Global Image Retouching

TL;DR

This paper introduces CSRNet, a lightweight and efficient global image retouching framework that uses conditional modulation and minimal parameters to achieve state-of-the-art results on benchmark datasets.

Contribution

The paper proposes CSRNet, a novel, extremely lightweight neural network for global image retouching that outperforms existing methods with fewer than 37k parameters.

Findings

Achieves state-of-the-art performance on MIT-Adobe FiveK dataset.

Contains less than 37,000 trainable parameters, significantly fewer than existing methods.

Demonstrates effective global image retouching through conditional modulation.

Abstract

Photo retouching aims at enhancing the aesthetic visual quality of images that suffer from photographic defects such as over/under exposure, poor contrast, inharmonious saturation. Practically, photo retouching can be accomplished by a series of image processing operations. In this paper, we investigate some commonly-used retouching operations and mathematically find that these pixel-independent operations can be approximated or formulated by multi-layer perceptrons (MLPs). Based on this analysis, we propose an extremely light-weight framework - Conditional Sequential Retouching Network (CSRNet) - for efficient global image retouching. CSRNet consists of a base network and a condition network. The base network acts like an MLP that processes each pixel independently and the condition network extracts the global features of the input image to generate a condition vector. To realize retouching operations, we modulate the intermediate features using Global Feature Modulation (GFM), of which the parameters are transformed by condition vector. Benefiting from the utilization of $1\times1$ convolution, CSRNet only contains less than 37k trainable parameters, which is orders of magnitude smaller than existing learning-based methods. Extensive experiments show that our method achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively. Code is available at https://github.com/hejingwenhejingwen/CSRNet.