从 legacy 到当代:长视频的可扩展色彩现代化
From Legacy to Contemporary: Scalable Color Modernization for Long Videos
AI总结:
针对长视频色彩现代化难题,提出无训练可扩展框架,结合文本引导图像编辑模型与镜头特定色彩变换,在多维度评估中实现最高感知当代感,为该领域系统研究开辟路径。
摘要:
将 legacy 视频适配到当代屏幕并不一定能使其呈现当代效果。早期成像流程常留下色偏、色度暗淡、对比度弱和色调失衡等问题,而修正这些问题仍高度依赖专业调色师,且难以扩展到长时长、多镜头的视频。本文提出长视频色彩现代化任务,该任务在保留场景内容及帧与镜头间连贯性的同时,更新 legacy 彩色素材的色度与色调外观。我们引入一种可扩展的无训练框架,利用预训练的文本引导图像编辑模型,联合现代化时间相邻关键帧网格,在无配对监督下生成连贯的当代参考。随后,紧凑的镜头特定色彩变换将这些调整传播到整个镜头,保留空间结构与时间稳定性。我们对跨越五个年代的多样 legacy 视频进行多维度评估,结合对当代感的人类评估,以及内容保真度、时间稳定性、感知质量和效率的量化测量,并提出源加权镜头间等级一致性(SW-IGC)以评估镜头间的等级连贯性。在评估集上,我们的框架实现了最高的感知当代感,同时在互补测量中保持竞争力,为长视频色彩现代化的系统研究开辟了道路。代码可访问此 https URL 此 https URL
英文摘要:
Bringing legacy video back to contemporary screens does not necessarily make it look contemporary. Earlier imaging pipelines often leave color casts, muted chroma, weak con- trast, and tonal imbalance, while correcting these character- istics still relies heavily on expert colorists and scales poorly to long, multi-shot videos. We formulate long video color modernization, a task that updates the chromatic and tonal appearance of legacy color footage while preserving scene content and coherence across frames and shots. We introduce a scalable, training-free framework that jointly modernizes grids of temporally adjacent keyframes using a pretrained text-guided image editing model, producing coherent con- temporary references without paired supervision. Compact shot-specific color transforms then propagate these adjust- ments throughout each shot, preserving spatial structure and temporal stability. We conduct a multidimensional evaluation on diverse legacy videos spanning five decades. We combine a human evaluation of perceived modernness with quantita- tive measures of content fidelity, temporal stability, percep- tual quality, and efficiency, and introduce Source-Weighted Inter-shot Grade Consistency (SW-IGC) to assess grade co- herence across shots. On our evaluation set, our frame- work achieves the highest perceived modernness while re- maining competitive across complementary measures, open- ing a path toward the systematic study of long video color modernization. Code is available at https://github.com/jiwoomood/ Video_Color_Modernization.git
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。