构建首个大规模合成HDR融合数据集，提升模型泛化能力。
S2R-HDR: A Large-Scale Rendered Dataset for HDR Fusion
- 用UE5生成24,000个高动态范围真实场景，涵盖多种运动与光照。
- 在真实数据集上达到当前最优的HDR融合效果。
- 提供领域自适应模块，有效缩小合成与真实数据差距。
基于学习的高动态范围（HDR）融合方法常因训练数据不足而泛化能力受限，因为从动态场景中采集大规模真实HDR图像既昂贵又技术困难。为此，我们提出S2R-HDR，首个大规模高质量的合成HDR融合数据集，包含24,000个样本。基于Unreal Engine 5，我们设计了涵盖多种动态元素、运动类型、高动态范围场景和光照条件的多样化真实感场景。此外，我们开发了一种高效的渲染流水线以生成逼真的HDR图像。为进一步缩小合成数据与真实世界之间的域差距，我们引入S2R-Adapter，一种专为该任务设计的域自适应方法，显著提升了模型的泛化能力。在真实世界数据集上的实验表明，本方法实现了当前最佳的HDR融合性能。数据集与代码已公开于https://openimaginglab.github.io/S2R-HDR。
原文摘要 · Abstract (English)
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 fusion performance. Dataset and code are available at https://openimaginglab.github.io/S2R-HDR.
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。