NOVA：稀疏控制与稠密合成的无配对视频编辑
NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing
用稀疏用户编辑关键帧提供语义引导、稠密分支从原视频持续注入运动与纹理，配合退化模拟训练摆脱配对数据，可直接迁移到无配对视频编辑与长视频时序一致性建模。
原文依据 the sparse branch provides semantic guidance through user-edited keyframes distributed across the video
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期的视频编辑模型已取得令人瞩目的成果，但大多数仍需要大规模配对数据集。在规模上采集这种自然对齐的配对数据仍然极具挑战，并构成了关键瓶颈，对局部视频编辑数据而言尤其如此。现有的一些变通做法通过全局运动控制将图像编辑迁移到视频，以实现无配对视频编辑，但这类设计在背景一致性和时序一致性上表现不佳。本文提出 NOVA：稀疏控制与稠密合成，一种新的视频编辑框架。具体而言，稀疏分支通过分布在视频各处的用户编辑关键帧提供语义引导，稠密分支则持续吸收原始视频中的运动与纹理信息，以保持高保真度与连贯性。此外，我们引入一种退化模拟训练策略，使模型能够通过在人工退化视频上训练来学习运动重建与时序一致性，从而无需配对数据。大量实验表明，NOVA 在编辑保真度、运动保持与时序连贯性上优于现有方法。
英文原文摘要 1188 字符
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 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.