Saved in:
Bibliographic Details
Main Authors: Xu, Chenyi, Wu, Yihao, Yan, Liqi, Yang, Chao, Zhang, Jianhui, Guan, Fangli, Li, Pan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.17303
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913136614834176
author Xu, Chenyi
Wu, Yihao
Yan, Liqi
Yang, Chao
Zhang, Jianhui
Guan, Fangli
Li, Pan
author_facet Xu, Chenyi
Wu, Yihao
Yan, Liqi
Yang, Chao
Zhang, Jianhui
Guan, Fangli
Li, Pan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17303
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos
Xu, Chenyi
Wu, Yihao
Yan, Liqi
Yang, Chao
Zhang, Jianhui
Guan, Fangli
Li, Pan
Computer Vision and Pattern Recognition
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.
title LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.17303