Discovering an Image-Adaptive Coordinate System for Photography Processing

TL;DR

This paper introduces IAC, an innovative method that learns an image-adaptive coordinate system in RGB space, enabling efficient and high-quality photography processing tasks with a lightweight and fast approach.

Contribution

The paper proposes a novel, end-to-end trainable algorithm that learns an image-adaptive coordinate system in RGB space for improved curve-based photo editing.

Findings

Achieves state-of-the-art performance in photo retouching, exposure correction, and white-balance editing.

Maintains a lightweight model with fast inference speed.

Outperforms existing methods in various photography processing tasks.

Abstract

Curve & Lookup Table (LUT) based methods directly map a pixel to the target output, making them highly efficient tools for real-time photography processing. However, due to extreme memory complexity to learn full RGB space mapping, existing methods either sample a discretized 3D lattice to build a 3D LUT or decompose into three separate curves (1D LUTs) on the RGB channels. Here, we propose a novel algorithm, IAC, to learn an image-adaptive Cartesian coordinate system in the RGB color space before performing curve operations. This end-to-end trainable approach enables us to efficiently adjust images with a jointly learned image-adaptive coordinate system and curves. Experimental results demonstrate that this simple strategy achieves state-of-the-art (SOTA) performance in various photography processing tasks, including photo retouching, exposure correction, and white-balance editing, while also maintaining a lightweight design and fast inference speed.