LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos

TL;DR

LongDPM introduces an overlap-aware framework for scalable, long-range 4D scene reconstruction from monocular videos, effectively connecting local predictions across chunks for coherent dynamic 3D modeling.

Contribution

It proposes a novel method that processes long videos in overlapping chunks, connecting local reconstructions into a unified long-range dynamic scene.

Findings

Reduces dense tracking EPE over V-DPM on PointOdyssey, Kubric-F, and Kubric-G datasets.

Achieves the best TUM-dynamics ATE for camera pose estimation.

Demonstrates superior long-range reconstruction and tracking performance.

Abstract

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.