Vista4D: Video Reshooting with 4D Point Clouds
2026-04-23 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors present Vista4D, a new method that lets you take a video and recreate the same scene and movement from different camera angles. Unlike past methods, their approach uses a 4D point cloud, which helps keep the scene’s details and camera control accurate, even when the scene is complex or changing. They also improve how the method handles depth and appearance, making the videos look better and behave more realistically. This technique works on real-world videos and can be used for things like expanding scenes or rearranging parts of a video.
4D point cloudvideo reshootingdynamic scenescamera trajectorydepth estimationmultiview reconstructionstatic pixel segmentationvisual consistencyscene recomposition
Authors
Kuan Heng Lin, Zhizheng Liu, Pablo Salamanca, Yash Kant, Ryan Burgert, Yuancheng Xu, Koichi Namekata, Yiwei Zhao, Bolei Zhou, Micah Goldblum, Paul Debevec, Ning Yu
Abstract
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