Complet4R: Geometric Complete 4D Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Weibang, Li, Kenan, Chen, Zhuoguang, Yuan, Yijun, Zhao, Hang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912986677903360
author Wang, Weibang
Li, Kenan
Chen, Zhuoguang
Yuan, Yijun
Zhao, Hang
author_facet Wang, Weibang
Li, Kenan
Chen, Zhuoguang
Yuan, Yijun
Zhao, Hang
contents We introduce Complet4R, a novel end-to-end framework for Geometric Complete 4D Reconstruction, which aims to recover temporally coherent and geometrically complete reconstruction for dynamic scenes. Our method formalizes the task of Geometric Complete 4D Reconstruction as a unified framework of reconstruction and completion, by directly accumulating full contexts onto each frame. Unlike previous approaches that rely on pairwise reconstruction or local motion estimation, Complet4R utilizes a decoder-only transformer to operate all context globally directly from sequential video input, reconstructing a complete geometry for every single timestamp, including occluded regions visible in other frames. Our method demonstrates the state-of-the-art performance on our proposed benchmark for Geometric Complete 4D Reconstruction and the 3D Point Tracking task. Code will be released to support future research.
format Preprint
id arxiv_https___arxiv_org_abs_2603_27300
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Complet4R: Geometric Complete 4D Reconstruction
Wang, Weibang
Li, Kenan
Chen, Zhuoguang
Yuan, Yijun
Zhao, Hang
Computer Vision and Pattern Recognition
We introduce Complet4R, a novel end-to-end framework for Geometric Complete 4D Reconstruction, which aims to recover temporally coherent and geometrically complete reconstruction for dynamic scenes. Our method formalizes the task of Geometric Complete 4D Reconstruction as a unified framework of reconstruction and completion, by directly accumulating full contexts onto each frame. Unlike previous approaches that rely on pairwise reconstruction or local motion estimation, Complet4R utilizes a decoder-only transformer to operate all context globally directly from sequential video input, reconstructing a complete geometry for every single timestamp, including occluded regions visible in other frames. Our method demonstrates the state-of-the-art performance on our proposed benchmark for Geometric Complete 4D Reconstruction and the 3D Point Tracking task. Code will be released to support future research.
title Complet4R: Geometric Complete 4D Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.27300