BlazeBVD：让尺度-时间均衡在盲视频去闪烁中重焕生机
BlazeBVD: Make Scale-Time Equalization Great Again for Blind Video Deflickering
AI总结：
针对盲视频去闪烁深度学习方法训练难、耗资源的问题，提出结合光照直方图与尺度-时间均衡的BlazeBVD方案，兼顾去闪烁效果与推理速度，性能优于现有最优方法。
摘要：
随着图像处理与视频生成技术蓬勃发展，开发用于提升视频时间一致性的盲视频去闪烁（BVD）算法愈发重要。但视频数据的复杂特性使深度学习方法的训练难度加大，导致资源消耗高且稳定性差，在严重光照闪烁场景下尤为明显，这凸显出突破像素值限制、寻找紧凑表征对推动BVD研究与应用的关键必要性。受经典尺度-时间均衡（STE）启发，本研究提出名为BlazeBVD的直方图辅助方案，实现高保真、快速的盲视频去闪烁。STE通过对颜色直方图进行时间平滑直接校正像素值，与之相比，BlazeBVD在STE滤波中利用平滑后的光照直方图，降低了神经网络学习时间序列数据的难度。技术层面，BlazeBVD首先将像素值压缩为光照直方图，精准捕捉闪烁与局部曝光变化；随后对这些直方图进行平滑处理，生成奇异帧集合、滤波后光照图与曝光图。借助这些去闪烁先验，BlazeBVD使用2D网络恢复受光照变化或局部曝光问题影响的真实一致纹理，同时引入轻量级3D网络修正细微时间不一致性，避免了高资源消耗问题。在合成视频、真实世界视频与生成视频上开展的综合实验表明，BlazeBVD在定性与定量结果上均表现优异，推理速度比现有最优方法最高快10倍。
英文摘要：
Developing blind video deflickering (BVD) algorithms to enhance video temporal consistency, is gaining importance amid the flourish of image processing and video generation. However, the intricate nature of video data complicates the training of deep learning methods, leading to high resource consumption and instability, notably under severe lighting flicker. This underscores the critical need for a compact representation beyond pixel values to advance BVD research and applications. Inspired by the classic scale-time equalization (STE), our work introduces the histogram-assisted solution, called BlazeBVD, for high-fidelity and rapid BVD. Compared with STE, which directly corrects pixel values by temporally smoothing color histograms, BlazeBVD leverages smoothed illumination histograms within STE filtering to ease the challenge of learning temporal data using neural networks. In technique, BlazeBVD begins by condensing pixel values into illumination histograms that precisely capture flickering and local exposure variations. These histograms are then smoothed to produce singular frames set, filtered illumination maps, and exposure maps. Resorting to these deflickering priors, BlazeBVD utilizes a 2D network to restore faithful and consistent texture impacted by lighting changes or localized exposure issues. BlazeBVD also incorporates a lightweight 3D network to amend slight temporal inconsistencies, avoiding the resource consumption issue. Comprehensive experiments on synthetic, real-world and generated videos, showcase the superior qualitative and quantitative results of BlazeBVD, achieving inference speeds up to 10x faster than state-of-the-arts.
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。
