超越生成：通过自监督微调解锁通用编辑
Beyond Generation: Unlocking Universal Editing via Self-Supervised Fine-Tuning
AI总结：
针对视频编辑依赖监督、生成与编辑割裂及训练成本高的问题，提出轻量级自监督微调策略 UES，并构建 OmniBench-99，实现通用统一编辑且保持生成能力。
摘要：
近期视频生成的进展已经超过视频编辑的发展，而视频编辑仍受若干限制因素约束，即：（a）该任务对监督的依赖严重限制了通用性，（b）生成与编辑任务之间不必要的人为割裂，以及（c）训练视频模型的高昂计算成本。在本文中，我们提出 UES（Unlocking Universal Editing via Self-Supervision，通过自监督解锁通用编辑），这是一种轻量级自监督微调策略，通过自监督语义对齐将生成模型转化为统一的生成—编辑系统。我们的方法建立了双条件机制，其中原始视频—文本对共同提供视觉和文本语义，从而实现对内在时空对应关系的结构化学习。关键优势包括：（i）通过无需监督地适配多种编辑任务实现通用性；（ii）统一生成与编辑，适用于大多数文本（+图像）到视频模型；以及（iii）通过轻量级微调实现高效性，将可训练参数减少 92.67%。为实现系统化评估，我们引入 OmniBench-99，这是一个综合基准，涵盖跨越人物/动物、环境和物体的 99 个视频，包含 4 种编辑类型和 8 个场景。大量实验表明，UES 使本身不具备编辑能力的模型能够执行强大而通用的编辑，同时保持甚至增强其原有生成性能。
英文摘要：
Recent advances in video generation have outpaced progress in video editing, which remains constrained by several limiting factors, namely: (a) the task's dependency on supervision severely limits generality, (b) an unnecessary artificial separation between the generation and editing task, and (c) the high computational costs of training a video model. In this work, we propose UES (Unlocking Universal Editing via Self-Supervision), a lightweight self-supervised fine-tuning strategy that transforms generation models into unified generation-editing systems through self-supervised semantic alignment. Our approach establishes a dual-conditioning mechanism where original video-text pairs jointly provide visual and textual semantics, enabling structured learning of intrinsic spatiotemporal correspondences. Key advantages include: (i) Universality through supervision-free adaptation to diverse editing tasks, (ii) Unification of generation and editing applicable to most text(+image)-to-video model, and (iii) Efficiency via lightweight fine-tune that reduces tunable parameters by 92.67%. To enable systematic evaluation, we introduce OmniBench-99, a comprehensive benchmark spanning 99 videos across humans/animals, environments, and objects, comprising 4 editing types and 8 scenarios. Extensive experiments show UES enables models without inherent editing capability to perform powerful and universal editing while preserving or even enhancing their original generation performance.
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。
