Saved in:
Bibliographic Details
Main Authors: Lin, Kuan Heng, Liu, Zhizheng, Salamanca, Pablo, Kant, Yash, Burgert, Ryan, Xu, Yuancheng, Namekata, Koichi, Zhao, Yiwei, Zhou, Bolei, Goldblum, Micah, Debevec, Paul, Yu, Ning
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.21915
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910160694280192
author Lin, Kuan Heng
Liu, Zhizheng
Salamanca, Pablo
Kant, Yash
Burgert, Ryan
Xu, Yuancheng
Namekata, Koichi
Zhao, Yiwei
Zhou, Bolei
Goldblum, Micah
Debevec, Paul
Yu, Ning
author_facet Lin, Kuan Heng
Liu, Zhizheng
Salamanca, Pablo
Kant, Yash
Burgert, Ryan
Xu, Yuancheng
Namekata, Koichi
Zhao, Yiwei
Zhou, Bolei
Goldblum, Micah
Debevec, Paul
Yu, Ning
contents We present Vista4D, a robust and flexible video reshooting framework that grounds the input video and target cameras in a 4D point cloud. Specifically, given an input video, our method re-synthesizes the scene with the same dynamics from a different camera trajectory and viewpoint. Existing video reshooting methods often struggle with depth estimation artifacts of real-world dynamic videos, while also failing to preserve content appearance and failing to maintain precise camera control for challenging new trajectories. We build a 4D-grounded point cloud representation with static pixel segmentation and 4D reconstruction to explicitly preserve seen content and provide rich camera signals, and we train with reconstructed multiview dynamic data for robustness against point cloud artifacts during real-world inference. Our results demonstrate improved 4D consistency, camera control, and visual quality compared to state-of-the-art baselines under a variety of videos and camera paths. Moreover, our method generalizes to real-world applications such as dynamic scene expansion and 4D scene recomposition. See our project page for results, code, and models: https://eyeline-labs.github.io/Vista4D
format Preprint
id arxiv_https___arxiv_org_abs_2604_21915
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Vista4D: Video Reshooting with 4D Point Clouds
Lin, Kuan Heng
Liu, Zhizheng
Salamanca, Pablo
Kant, Yash
Burgert, Ryan
Xu, Yuancheng
Namekata, Koichi
Zhao, Yiwei
Zhou, Bolei
Goldblum, Micah
Debevec, Paul
Yu, Ning
Computer Vision and Pattern Recognition
We present Vista4D, a robust and flexible video reshooting framework that grounds the input video and target cameras in a 4D point cloud. Specifically, given an input video, our method re-synthesizes the scene with the same dynamics from a different camera trajectory and viewpoint. Existing video reshooting methods often struggle with depth estimation artifacts of real-world dynamic videos, while also failing to preserve content appearance and failing to maintain precise camera control for challenging new trajectories. We build a 4D-grounded point cloud representation with static pixel segmentation and 4D reconstruction to explicitly preserve seen content and provide rich camera signals, and we train with reconstructed multiview dynamic data for robustness against point cloud artifacts during real-world inference. Our results demonstrate improved 4D consistency, camera control, and visual quality compared to state-of-the-art baselines under a variety of videos and camera paths. Moreover, our method generalizes to real-world applications such as dynamic scene expansion and 4D scene recomposition. See our project page for results, code, and models: https://eyeline-labs.github.io/Vista4D
title Vista4D: Video Reshooting with 4D Point Clouds
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.21915