LiBrA-Net：利用李代数双侧仿射场实现实时4K视频去雾
LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing
AI总结：
本文提出LiBrA-Net，通过李代数双侧仿射场实现高效4K视频去雾，同时发布首个带有深度、传输和光流标注的4K视频去雾基准UHV-4K，达到25 FPS的实时处理速度。
摘要：
目前，由于缺乏评估基准，超高清（UHD）视频去雾领域存在空白。现有方法在处理连续UHD序列时无法在消费级GPU上运行。本文通过新的基准和高效方法解决这两个问题。我们的关键观察是大气去雾可以归结为由低频深度场支配的每像素仿射变换，可通过双侧网格紧凑编码。基于此，我们提出LiBrA-Net，将时空仿射场分解为空间-颜色和时间双侧子网格，在固定低分辨率下预测，通过群论正则化在$\mathfrak{gl}(3)$李代数下融合系数，通过凯莱参数化映射到可逆GL(3)变换，并通过轻量级输入引导分支恢复高频细节。我们还发布了UHV-4K，首个带有深度、传输和光流标注的4K视频去雾基准。在UHV-4K、REVIDE和HazeWorld上，LiBrA-Net在对比视频去雾方法中达到新的SOTA，可在单GPU上以25 FPS运行4K，仅需6.12 M参数。代码和数据可在https://anonymous.4open.science/r/LiBrA-Net-42B8获取。
英文摘要：
Currently, there is a gap in the field of ultra-high-definition (UHD) video dehazing due to the lack of a benchmark for evaluation. Furthermore, existing video dehazing methods cannot run on consumer-grade GPUs when processing continuous UHD sequences of 3--5 frames at a time. In this paper, we address both issues with a new benchmark and an efficient method. Our key observation is that atmospheric dehazing reduces to a per-pixel affine transform governed by the low-frequency depth field, which can be compactly encoded in bilateral grids whose prediction cost is decoupled from the output resolution. Building on this, we propose LiBrA-Net, which factorizes the spatiotemporal affine field into a spatial--color and a temporal bilateral sub-grid predicted at a fixed low resolution, fuses their coefficients in the $\mathfrak{gl}(3)$ Lie algebra under group-theoretic regularization, maps the result to invertible GL(3) transforms via a Cayley parameterization, and restores high-frequency detail through a lightweight input-guided branch. We further release UHV-4K, the first paired 4K video dehazing benchmark with depth, transmission, and optical-flow annotations on every frame. Across UHV-4K, REVIDE, and HazeWorld, LiBrA-Net sets a new state of the art among compared video dehazing methods while running native 4K at 25 FPS on a single GPU with only 6.12 M parameters. Code and data are available at https://anonymous.4open.science/r/LiBrA-Net-42B8.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
