Saved in:
Bibliographic Details
Main Authors: Pan, Weihong, Zhang, Xiaoyu, Zhang, Zhuang, Ye, Zhichao, Wang, Nan, Liu, Haomin, Zhang, Guofeng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.26481
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918430459822080
author Pan, Weihong
Zhang, Xiaoyu
Zhang, Zhuang
Ye, Zhichao
Wang, Nan
Liu, Haomin
Zhang, Guofeng
author_facet Pan, Weihong
Zhang, Xiaoyu
Zhang, Zhuang
Ye, Zhichao
Wang, Nan
Liu, Haomin
Zhang, Guofeng
contents High-quality 4D reconstruction enables photorealistic and immersive rendering of the dynamic real world. However, unlike static scenes that can be fully captured with a single camera, high-quality dynamic scenes typically require dense arrays of tens or even hundreds of synchronized cameras. Dependence on such costly lab setups severely limits practical scalability. To this end, we propose a sparse-camera dynamic reconstruction framework that exploits abundant yet inconsistent generative observations. Our key innovation is the Spatio-Temporal Distortion Field, which provides a unified mechanism for modeling inconsistencies in generative observations across both spatial and temporal dimensions. Building on this, we develop a complete pipeline that enables 4D reconstruction from sparse and uncalibrated camera inputs. We evaluate our method on multi-camera dynamic scene benchmarks, achieving spatio-temporally consistent high-fidelity renderings and significantly outperforming existing approaches. Project page available at https://inspatio.github.io/sparse-cam4d/
format Preprint
id arxiv_https___arxiv_org_abs_2603_26481
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SparseCam4D: Spatio-Temporally Consistent 4D Reconstruction from Sparse Cameras
Pan, Weihong
Zhang, Xiaoyu
Zhang, Zhuang
Ye, Zhichao
Wang, Nan
Liu, Haomin
Zhang, Guofeng
Computer Vision and Pattern Recognition
High-quality 4D reconstruction enables photorealistic and immersive rendering of the dynamic real world. However, unlike static scenes that can be fully captured with a single camera, high-quality dynamic scenes typically require dense arrays of tens or even hundreds of synchronized cameras. Dependence on such costly lab setups severely limits practical scalability. To this end, we propose a sparse-camera dynamic reconstruction framework that exploits abundant yet inconsistent generative observations. Our key innovation is the Spatio-Temporal Distortion Field, which provides a unified mechanism for modeling inconsistencies in generative observations across both spatial and temporal dimensions. Building on this, we develop a complete pipeline that enables 4D reconstruction from sparse and uncalibrated camera inputs. We evaluate our method on multi-camera dynamic scene benchmarks, achieving spatio-temporally consistent high-fidelity renderings and significantly outperforming existing approaches. Project page available at https://inspatio.github.io/sparse-cam4d/
title SparseCam4D: Spatio-Temporally Consistent 4D Reconstruction from Sparse Cameras
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.26481