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

TL;DR

This paper introduces RawHDR, a novel method for reconstructing high dynamic range images directly from raw sensor data, leveraging unique raw features and guidance mechanisms to improve scene detail recovery, especially in extreme regions.

Contribution

It presents a specialized Raw-to-HDR model with exposure masks and guidance strategies, along with a new large Raw/HDR dataset for training and evaluation.

Findings

RawHDR outperforms existing methods in HDR reconstruction quality.

The dataset enables robust training and evaluation of Raw-to-HDR models.

Guidance mechanisms effectively improve scene detail recovery in challenging regions.

Abstract

High dynamic range (HDR) images capture much more intensity levels than standard ones. Current methods predominantly generate HDR images from 8-bit low dynamic range (LDR) sRGB images that have been degraded by the camera processing pipeline. However, it becomes a formidable task to retrieve extremely high dynamic range scenes from such limited bit-depth data. 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). To this end, we propose a model tailor-made for Raw images, harnessing the unique features of Raw data to facilitate 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 extrapolates scene specifics over an extended spatial domain. To verify our Raw-to-HDR approach, we collect a large Raw/HDR paired dataset for both training and testing. Our empirical evaluations validate the superiority of the proposed Raw-to-HDR reconstruction model, as well as our newly captured dataset in the experiments.