NOVA：无配对视频编辑的稀疏控制与密集合成
NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing
AI总结：
NOVA提出了一种无配对视频编辑框架，通过稀疏控制与密集合成提升编辑保真度和时间一致性。
摘要：
近年来，视频编辑模型取得了令人印象深刻的结果，但大多数仍然需要大规模配对数据集。收集这种自然对齐的配对在大规模上仍然极具挑战性，尤其是在局部视频编辑数据方面构成关键瓶颈。现有工作通过全局运动控制将图像编辑转移到视频，实现无配对视频编辑，但此类设计在背景和时间一致性方面存在困难。在本文中，我们提出了NOVA：稀疏控制与密集合成，一种新的无配对视频编辑框架。具体而言，稀疏分支通过分布在视频中的用户编辑关键帧提供语义指导，而密集分支持续整合原始视频中的运动和纹理信息，以保持高保真度和一致性。此外，我们引入了一种退化模拟训练策略，通过在人工退化视频上训练，使模型能够学习运动重建和时间一致性，从而消除对配对数据的需求。我们的大量实验表明，NOVA在编辑保真度、运动保持和时间一致性方面均优于现有方法。
英文摘要：
Recent video editing models have achieved impressive results, but most still require large-scale paired datasets. Collecting such naturally aligned pairs at scale remains highly challenging and constitutes a critical bottleneck, especially for local video editing data. Existing workarounds transfer image editing to video through global motion control for pair-free video editing, but such designs struggle with background and temporal consistency. In this paper, we propose NOVA: Sparse Control \& Dense Synthesis, a new framework for unpaired video editing. Specifically, the sparse branch provides semantic guidance through user-edited keyframes distributed across the video, and the dense branch continuously incorporates motion and texture information from the original video to maintain high fidelity and coherence. Moreover, we introduce a degradation-simulation training strategy that enables the model to learn motion reconstruction and temporal consistency by training on artificially degraded videos, thus eliminating the need for paired data. Our extensive experiments demonstrate that NOVA outperforms existing approaches in edit fidelity, motion preservation, and temporal coherence.
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。
