发表机构
Hangzhou Dianzi University; Zhejiang Provincial Key Laboratory of Low Altitude Ubiquitous Networking Technology, Hangzhou Dianzi University; Institute of Microelectronics, Chinese Academy of Sciences; University of Chinese Academy of Sciences; Beijing Institute of Technology（杭州电子科技大学; 浙江省低空泛在组网技术重点实验室，杭州电子科技大学; 中国科学院微电子研究所; 中国科学院大学; 北京理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对单曝光原始视频的HDR重建难题，提出RawHDRV端到端框架，利用Bayer数据线性响应与通道特性，结合通道分解对齐融合、曝光互补掩码恢复及掩码引导颜色损失，构建大规模数据集，实现最先进性能。
AI 中文摘要
由于传统图像传感器的动态范围有限，捕获的低动态范围（LDR）视频常常遭受高光裁剪和阴影细节丢失，这使得在不交替曝光或使用额外硬件的情况下，从单曝光序列进行高质量高动态范围（HDR）重建极具挑战性。交替曝光的HDR方法牺牲了帧率，并难以处理运动对齐问题，使其在实际拍摄中不实用。为解决这一问题，我们提出了RawHDRV，一个用于单曝光原始视频HDR重建的端到端框架，该框架从根本上利用了Bayer数据的线性响应和通道特定特性。具体而言，它采用了一种通道分解的时间对齐与融合策略，分别处理Bayer通道以利用其不同的曝光特性，并结合曝光感知的加权融合。此外，该框架还引入了一个曝光互补掩码引导的恢复模块，利用帧间曝光冗余自适应地融合可靠信息并抑制饱和伪影，并提出了一种掩码引导的颜色损失，将归一化误差约束与梯度平滑相结合以增强高光恢复。进一步地，我们构建了一个大规模移动原始HDR视频数据集，并带有逐帧HDR标注。实验表明，我们的方法在所有指标上达到了最先进的结果，展示了在极端曝光条件下优越的空间质量和时间稳定性。代码可在https://github.com/supeixian/RawHDRV获取。
英文摘要
Due to the limited dynamic range of conventional image sensors, captured low dynamic range (LDR) video often suffers from highlight clipping and shadow detail loss, making high-quality high dynamic range (HDR) reconstruction from single-exposure sequences highly challenging without alternating exposures or extra hardware. Alternating-exposure HDR methods sacrifice frame rate and struggle with motion alignment, making them impractical for real-world capture. To address this, we propose RawHDRV, an end-to-end framework for single-exposure Raw video HDR reconstruction, that fundamentally exploits the linear response and channel-specific characteristics of Bayer data. Specifically, it features a channel-decomposition temporal alignment and fusion strategy that processes Bayer channels separately to exploit their distinct exposure characteristics, together with exposure-aware weighted fusion. It further incorporates an exposure complementarity mask-guided restoration module that leverages inter-frame exposure redundancy to adaptively fuse reliable information and suppress saturation artifacts, and introduces a mask-guided color loss that combines normalized error constraints with gradient smoothing to enhance highlight recovery. Furthermore, we construct a large-scale mobile Raw-HDR video dataset with per-frame HDR annotations. Experiments show that our method achieves the state-of-the-art results in all metrics, demonstrating superior spatial quality and temporal stability under extreme exposure conditions. The code is available at https://github.com/supeixian/RawHDRV.
Comments12 pages. Code: https://github.com/supeixian/RawHDRV
