检索缺失内容：面向一致长视频生成的覆盖最大化检索
Retrieve What's Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation
AI总结：
提出基于深度的覆盖最大化检索增强生成框架COVRAG，利用预训练3D先验构建轻量级覆盖图作为记忆证据，通过迭代检索最大化残差覆盖来提升长视频生成的几何一致性。
摘要：
对于长时域自回归视频生成，保持长期几何一致性仍然具有挑战性。记忆增强生成模型通过检索历史帧来解决这一问题，但其有效性取决于两个关键设计选择：哪些3D几何证据应代表过去的观测，以及如何从这些证据中选择记忆帧。现有方法通常依赖相机位姿或视场重叠，这些方法轻量但过于粗糙，无法推理像素级可见性；或者使用显式3D重建，提供细粒度证据但在长序列中维护成本高昂。我们提出覆盖最大化检索增强生成（COVRAG），一种基于深度的记忆检索框架，利用预训练3D先验构建目标视图覆盖图作为轻量级3D记忆证据。在帧选择方面，COVRAG最大化残差覆盖增益，迭代检索能够解释当前上下文或先前选择的记忆未覆盖的目标视图区域的帧。为了提高长视频生成的可扩展性，我们引入滑动窗口深度缓存以实现高效的几何估计。在RealEstate10K和DL3DV10K上的实验表明，COVRAG在保持低延迟的同时，相比基线方法改善了长时域几何一致性。
英文摘要：
Maintaining long-term geometric consistency remains challenging for long-horizon autoregressive video generation. Memory-augmented generative models address this by retrieving historical frames, but their effectiveness depends on two key design choices: what 3D-geometric evidence should represent past observations, and how memory frames should be selected from this evidence. Existing methods often rely on camera poses or field-of-view overlap, which are lightweight but too coarse to reason about pixel-wise visibility, or use explicit 3D reconstruction, which provides fine-grained evidence but is costly to maintain over long rollouts. We propose Coverage-Maximizing Retrieval-Augmented Generation (COVRAG), a depth-based memory retrieval framework that uses pretrained 3D priors to construct a target-view coverage map as lightweight 3D memory evidence. For frame selection, COVRAG maximizes residual coverage gain, iteratively retrieving frames that explain target-view regions not covered by the current context or previously selected memories. To improve scalability in long-video generation, we introduce sliding-window depth caching for efficient geometry estimation. Experiments on RealEstate10K and DL3DV10K show that COVRAG improves long-horizon geometric consistency while maintaining low latency compared to baselines.
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。
