S2R-HDR: A Large-Scale Rendered Dataset for HDR Fusion
This addresses the data scarcity problem for researchers and practitioners in HDR imaging, though it is incremental as it builds on existing synthetic data methods.
The authors tackled the limited generalization of learning-based high dynamic range (HDR) fusion due to scarce training data by creating S2R-HDR, a large-scale synthetic dataset with 24,000 HDR samples, and achieved state-of-the-art HDR reconstruction performance on real-world datasets.
The generalization of learning-based high dynamic range (HDR) fusion is often limited by the availability of training data, as collecting large-scale HDR images from dynamic scenes is both costly and technically challenging. To address these challenges, we propose S2R-HDR, the first large-scale high-quality synthetic dataset for HDR fusion, with 24,000 HDR samples. Using Unreal Engine 5, we design a diverse set of realistic HDR scenes that encompass various dynamic elements, motion types, high dynamic range scenes, and lighting. Additionally, we develop an efficient rendering pipeline to generate realistic HDR images. To further mitigate the domain gap between synthetic and real-world data, we introduce S2R-Adapter, a domain adaptation designed to bridge this gap and enhance the generalization ability of models. Experimental results on real-world datasets demonstrate that our approach achieves state-of-the-art HDR reconstruction performance. Dataset and code will be available at https://openimaginglab.github.io/S2R-HDR.