LongDPM: 长视频中基于重叠意识的4D重建
LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos
AI总结：
本文提出LongDPM，一种基于重叠意识的长视频单目动态重建框架，通过分块处理、重登记和动态身份关联，实现长距离的3D重建和跟踪，提升了PointOdyssey、Kubric-F和Kubric-G等数据集上的密集跟踪精度和相机姿态估计性能。
摘要：
从长单目视频中恢复动态3D场景对于保持共享坐标系中密集几何、相机运动和时间对应的一致性至关重要。现有方法面临两个关键挑战：（1）前馈重建模型提供准确的局部预测，但仅限于短片段；（2）长距离跟踪器保持对应关系但不产生密集序列级重建。本文提出LongDPM，一种新的重叠意识框架，用于可扩展的长距离单目动态重建。首先，LongDPM通过重叠分块处理长视频，使推理内存受限于分块长度。其次，它通过带有静态意识的重叠抽象进行置信度加权注册，连接分块局部坐标系统。第三，它在分块边界处关联动态身份，并融合匹配轨迹以恢复连贯的长距离3D运动。实验结果表明，LongDPM在长距离重建和跟踪性能上优于现有方法，在PointOdyssey、Kubric-F和Kubric-G数据集上减少了密集跟踪EPE，同时在相机姿态估计方面获得了最佳TUM-dynamics ATE。
英文摘要：
Recovering a dynamic 3D scene from a long monocular video is crucial for dense geometry, camera motion, and temporal correspondence to remain consistent in a shared coordinate system. Existing methods face two key challenges: (1) feed-forward reconstruction models provide accurate local predictions but are limited to short clips, and (2) long-range trackers preserve correspondences without producing dense sequence-level reconstruction. This paper presents LongDPM, a novel overlap-aware framework for scalable long-range monocular dynamic reconstruction. First, LongDPM processes long videos in overlapping chunks, keeping inference memory bounded by the chunk length. Second, it connects chunk-local coordinate systems through confidence-weighted registration with static-aware overlap abstraction. Third, it associates dynamic identities across chunk boundaries and fuses matched trajectories to recover coherent long-range 3D motion. Experimental results demonstrate that LongDPM achieves superior long-range reconstruction and tracking performance, reducing dense tracking EPE over V-DPM on PointOdyssey, Kubric-F, and Kubric-G, while obtaining the best TUM-dynamics ATE for camera pose estimation.
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。
