Discovering an Image-Adaptive Coordinate System for Photography Processing
This work addresses the need for efficient and high-quality image processing tools for photographers and real-time applications, though it is incremental in improving existing curve and LUT methods.
The paper tackled the problem of efficient real-time photography processing by proposing IAC, a method that learns an image-adaptive coordinate system in RGB space before curve operations, achieving state-of-the-art performance in tasks like photo retouching, exposure correction, and white-balance editing with lightweight and fast inference.
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.