F^2HDR：通过光流适配器与物理运动建模的两阶段 HDR 视频重建
F^2HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling
论文提出的光流适配器可将通用光流模型适配到跨曝光对齐任务，这种轻量适配思路可迁移到其他需要跨域光流估计的视觉任务（如视频去噪、去模糊中的对齐）；物理运动建模用于识别显著运动区域，为动态场景下的特征聚合提供了一种可复用的运动先验注入方式。
原文依据 a flow adapter that adapts generic optical flow for robust cross-exposure alignment
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从交替曝光的低动态范围（LDR）帧序列中重建高动态范围（HDR）视频仍然极具挑战性，尤其是在动态场景下，跨曝光不一致性和复杂运动使得帧间对齐困难，导致鬼影和细节丢失。现有方法往往存在对齐不准确、特征聚合次优以及在运动主导区域重建质量下降的问题。为解决这些挑战，我们提出 F^2HDR，一个两阶段 HDR 视频重建框架，能够在复杂动态场景中鲁棒地感知帧间运动并恢复精细细节。该框架集成了一个光流适配器，用于适配通用光流以实现鲁棒的跨曝光对齐；一个物理运动建模，用于识别显著运动区域；以及一个运动感知细化网络，用于聚合互补信息同时去除鬼影和噪声。大量实验表明，F^2HDR 在真实世界 HDR 视频基准上达到了最优性能，在大运动和曝光变化下产生无鬼影且高保真的结果。我们的代码可在 https://github.com/wei1895/F2HDR 获取。
英文原文摘要 1222 字符
Reconstructing High Dynamic Range (HDR) videos from sequences of alternating-exposure Low Dynamic Range (LDR) frames remains highly challenging, especially under dynamic scenes where cross-exposure inconsistencies and complex motion make inter-frame alignment difficult, leading to ghosting and detail loss. Existing methods often suffer from inaccurate alignment, suboptimal feature aggregation, and degraded reconstruction quality in motion-dominated regions. To address these challenges, we propose F^2HDR, a two-stage HDR video reconstruction framework that robustly perceives inter-frame motion and restores fine details in complex dynamic scenarios. The proposed framework integrates a flow adapter that adapts generic optical flow for robust cross-exposure alignment, a physical motion modeling to identify salient motion regions, and a motion-aware refinement network that aggregates complementary information while removing ghosting and noise. Extensive experiments demonstrate that F^2HDR achieves state-of-the-art performance on real-world HDR video benchmarks, producing ghost-free and high-fidelity results under large motion and exposure variations. Our code is available at https://github.com/wei1895/F2HDR.