用可学习的色彩矩阵还原RAW图像，提升自动驾驶感知性能。
A Learnable Color Correction Matrix for RAW Reconstruction
- 设计轻量级可学习色彩校正矩阵，仅用一个卷积层模拟反向ISP。
- 生成的模拟RAW图像在预训练目标检测器时效果媲美复杂方法。
- 适合需要高效模拟真实驱动数据的研究者使用。
自动驾驶算法通常采用与人类视觉系统兼容的sRGB图像作为输入，但视觉上美观的sRGB图像可能对下游任务不如原始的RAW图像。由于真实驾驶数据采集困难及标注挑战，获取高质量的RAW图像受限。为解决此问题并支持原始域下的驾驶感知研究，本文提出一种新颖且超轻量级的RAW重建方法。该模型引入一个可学习的色彩校正矩阵（CCM），仅通过单个卷积层即可近似复杂的反向图像信号处理器（inverse ISP）。实验结果表明，在预训练原始域目标检测器时，本方法生成的模拟RAW（simRAW）图像性能等同于更复杂反向ISP方法，充分证明了该方法的有效性与实用性。
原文摘要 · Abstract (English)
Autonomous driving algorithms usually employ sRGB images as model input due to their compatibility with the human visual system. However, visually pleasing sRGB images are possibly sub-optimal for downstream tasks when compared to RAW images. The availability of RAW images is constrained by the difficulties in collecting real-world driving data and the associated challenges of annotation. To address this limitation and support research in RAW-domain driving perception, we design a novel and ultra-lightweight RAW reconstruction method. The proposed model introduces a learnable color correction matrix (CCM), which uses only a single convolutional layer to approximate the complex inverse image signal processor (ISP). Experimental results demonstrate that simulated RAW (simRAW) images generated by our method provide performance improvements equivalent to those produced by more complex inverse ISP methods when pretraining RAW-domain object detectors, which highlights the effectiveness and practicality of our approach.
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。