让视频编辑既保真又扩展，解决遮挡与视角外内容生成难题
Preserve, Reveal, Expand: Faithful 4D Video Editing with Region-Aware Conditioning
- 分区域处理：将视频时空体分为保留、揭示、扩展三类角色
- 提升保真度：在基准测试中减少结构化错误，视觉质量更稳定
- 无需配对数据：通过代理任务训练，适合真实场景的精准编辑
现有4D驱动视频扩散模型主要关注生成合理性，但忠实的4D编辑需保留源观察区域的同时合成被遮挡或视域外内容。我们识别出‘证据-角色错配’问题：可靠源证据、不可靠生成提示与无支持区域混杂于单一条件信号中，导致保留漂移、鬼影和不稳定外推。提出PREX（Preserve, Reveal, Expand）框架，根据观测支持与场景范围将目标时空体分解为保留、揭示、扩展三类角色。PREX构建带置信度校准的观测支撑外观线索，并通过区域感知适配器注入冻结的视频扩散主干网络，采用代理任务训练，无需成对编辑视频。进一步引入PREBench诊断基准，包含精心策划的编辑、区域角色掩码及人类对齐指标，补充全局视频质量与4D控制评估。实验表明，PREX在保持强视觉质量与4D编辑控制能力的同时，显著减少结构性失败。
原文摘要 · Abstract (English)
Existing 4D-driven video diffusion models primarily target plausible generation, but faithful 4D editing requires preserving source-observed regions while synthesizing disoccluded or out-of-view content. We identify Evidence-Role Mismatch: reliable source-backed evidence, unreliable rendered cues, and unsupported regions are entangled in a single conditioning signal, causing preservation drift, ghosting, and unstable extrapolation. We propose PREX (Preserve, Reveal, Expand), a region-aware framework that decomposes the target spatiotemporal volume into Preserve, Reveal, and Expand roles according to observation support and scene extent. PREX builds observation-backed appearance cues with calibrated confidence and injects them into a frozen video diffusion backbone through a region-aware adapter, trained with proxy tasks without requiring paired edited videos. We further introduce PREBench, a diagnostic benchmark with curated edits, region-role masks, and human-aligned metrics that complement global video-quality and 4D-control evaluations. Experiments show that PREX reduces region-structured failures while maintaining strong visual quality and 4D edit control capability. Project Page: https://ricepastem.github.io/PREX-Open
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。