保留、揭示、扩展：基于区域感知的4D视频编辑
Preserve, Reveal, Expand: Towards Faithful 4D Video Editing with Region-Aware Conditioning and Benchmarking
AI总结：
本文提出PREX框架，通过区域感知分解目标时空体积，解决4D视频编辑中区域保持、揭示和扩展的问题，提升了视频编辑的准确性和稳定性。
摘要：
现有的4D驱动视频扩散模型主要针对合理生成，但忠实的4D编辑需要在合成遮挡或视外内容时保留源观测区域。我们识别出证据角色不匹配问题：可靠的源支持证据、不可靠的渲染提示和不支持的区域在单一条件信号中交织，导致保留漂移、鬼影和不稳定的外推。我们提出PREX（保留、揭示、扩展），一个区域感知框架，根据观测支持和场景范围将目标时空体积分解为保留、揭示和扩展角色。PREX通过校准置信度构建观测支持的外观提示，并通过区域感知适配器注入到冻结的视频扩散骨干网络中，通过代理任务训练而无需配对编辑视频。我们进一步引入PREBench，一个诊断基准，包含精心编辑、区域角色掩码和人类对齐的指标，补充了全局视频质量和4D控制评估。实验表明，PREX在减少区域结构失败的同时，保持了强大的视觉质量和4D编辑控制能力。项目页面：https://ricepastem.github.io/PREX-Open
英文摘要：
While 4D-driven video diffusion models can generate visually plausible videos, faithful 4D editing poses a stricter requirement: source-observed content should be preserved, while disoccluded and out-of-view regions must be synthesized naturally. We identify a key failure mode in existing methods, which we term Evidence-Role Mismatch: source-backed observations, uncertain rendered cues, and unsupported regions are entangled within a single conditioning signal, which can lead to preservation drift, ghosting, and unstable extrapolation. To mitigate this issue, we propose PREX (Preserve, Reveal, Expand), a region-aware framework that decomposes the target spatiotemporal volume into three distinct roles based on observation support and scene extent. PREX traces edited 4D points back to source frames and retrieves observed colors and pairs these appearance cues with geometry-aware confidence and region roles, and injects them into a frozen video diffusion backbone through an adapter trained with self-supervised proxy editing tasks. We further introduce PREBench, a diagnostic benchmark specifically designed for 4D video editing, to expose and quantify such region-specific failures. PREBench separately evaluates Preserve fidelity, Reveal quality, and Expand plausibility of videos generated by 4D driven video diffusion models. Experiments show that PREX substantially reduces region-specific failure modes while maintaining strong visual quality and 4D edit control compared with existing 4D-based video diffusion methods. Code will be publicly released. Project Page: https://ricepastem.github.io/PREX-Open
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。
