AI Paper Atlas

Research map / Point clouds / Point cloud classification

Vista4D: Video Reshooting with 4D Point Clouds

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

CVPR 2026 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add training with depth artifacts and in-context source video conditioning (ablation)Vista4D · robustness to 4D reconstruction artifactsqualitativeImproved
add temporal persistence of the 4D point cloud (ablation)Vista4D · low-overlap source video and target camerasstatic content preservation and camera accuracyImproved
use point-cloud conditioning with 4D grounding vs implicit-prior ReCamMasterVista4D · camera controltranslation error: 1.574 -> 1.251Improved
use Vista4D instead of GEN3CVista4D · 3D consistencyRE@SG: 12.99 -> 7.504Improved
use Vista4D instead of GEN3CVista4D · iPhone novel-view synthesisEPE: 3.019 -> 1.142Improved
use Vista4D instead of TrajectoryCrafterVista4D · iPhone novel-view synthesisSSIM: 0.320 -> 0.310Hurt
use Vista4D instead of ReCamMasterVista4D · video fidelityFID: 94.15 -> 105.4Hurt
use Vista4D instead of GEN3CVista4D · video fidelityFID: 113.5 -> 105.4Improved
use Vista4D instead of TrajectoryCrafterVista4D · VBench human anatomyhuman anatomy: 0.790 -> 0.857Improved
use Vista4D instead of GEN3CVista4D · user study overall fidelitypreference: 5.952% -> 77.38%Improved
use Vista4D 1280x720 instead of 672x384Vista4D · inference timemodel inference (s): 1195 -> 9924Hurt
use segmentation failure (racket not segmented)Vista4D · qualitativestreaking artifactsNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy