提出自适应坐标系，让照片处理更准更快。
Discovering an Image-Adaptive Coordinate System for Photography Processing
- 在RGB空间学习随图像变化的自适应坐标系，再做曲线映射。
- 在修图、曝光、白平衡任务上达到顶尖效果。
- 轻量设计，推理速度快，适合实时应用。
基于曲线与查找表（LUT）的方法直接将像素映射到目标输出，是实时摄影处理的高效工具。然而，由于学习完整RGB空间映射存在极高的内存开销，现有方法通常采用离散3D网格构建3D LUT，或对RGB三通道分别进行一维曲线（1D LUT）分解。本文提出一种新算法IAC，先在RGB颜色空间中学习图像自适应的笛卡尔坐标系，再执行曲线操作。该端到端可训练方法使我们能够联合学习自适应坐标系与曲线，实现高效图像调整。实验表明，这一简单策略在照片润色、曝光校正和白平衡编辑等任务中均达到当前最优性能，同时保持轻量化设计和快速推理速度。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。