RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image

Yunhao Zou, Chenggang Yan, Ying Fu; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 12334-12344

High dynamic range (HDR) images can record much more intensity levels than usual ones. Existing methods mainly reconstruct HDR images from the 8-bit low dynamic range (LDR) sRGB images that have been degraded by the camera processing pipeline. However, recovering extremely high dynamic range scenes from such low bit-depth data is challenging. Unlike existing methods, the core idea of this work is to incorporate more informative Raw sensor data to generate HDR images, aiming to recover scene information in hard regions (the darkest and brightest areas of an HDR scene). We propose a model customized for Raw images, considering the unique feature of Raw data to learn the Raw-to-HDR mapping. Specifically, we learn exposure masks to separate the hard and easy regions of a high dynamic scene. Then, we introduce two important guidances, dual intensity guidance, which guides less informative channels with more informative ones, and global spatial guidance which hallucinates scene details from a longer spatial range. To verify our Raw-to-HDR approach, we collect a large and high-quality Raw/HDR paired dataset for both training and testing, which will be made available publicly. We verify the superiority of the proposed Raw-to-HDR reconstruction model, as well as our newly captured dataset in the experiments.