Track2View: 4D-Consistent Camera-Controlled Video Generation via Paired 3D Point Tracks

2026-06-13

AI Summary

Existing video re-rendering methods struggle to simultaneously preserve appearance fidelity, ensure dynamic consistency, and enable precise camera control under novel viewpoints, while lacking explicit spatiotemporal pixel correspondences. To address these limitations, this work proposes a video diffusion Transformer conditioned on paired 3D point trajectories, achieving four-dimensional consistent and camera-controllable generation. The key innovations include a data pipeline that extracts one-to-one trajectory correspondences from multi-view videos and a dual-view trajectory conditioner that integrates geometric operations with temporal aggregation. Evaluated on a benchmark of 400 videos encompassing both static and dynamic scenes, the proposed method substantially outperforms existing approaches, reducing rotation errors by 30–65% and translation errors by 61–72%.

Abstract

Re-rendering an existing video from a novel camera viewpoint requires the output to follow the prescribed camera trajectory while preserving the appearance and dynamics of the original scene across every frame. Existing methods rely on per-frame pose embeddings, noisy point-cloud renderings, or implicit learned correspondences, none of which provides an explicit, temporally continuous link between source and target pixels. We propose Track2View, which conditions a video diffusion transformer on paired 3D point tracks: sparse trajectories of scene points projected into both the source and target camera views. These tracks provide explicit spatiotemporal correspondences that are temporally continuous by construction, encoding what content should appear where and when. At the core of Track2View is a dual-view track conditioner that transfers visual context from source to target view through parameter-free geometric operations and learned temporal aggregation, ensuring generalization to arbitrary camera trajectories without memorizing specific motions. We further introduce a data curation pipeline that extracts one-to-one track correspondences by running a 3D point tracker on temporally concatenated multi-camera view pairs. On a 400-video benchmark spanning static and dynamic scenes, Track2View achieves state-of-the-art results across visual quality, view synchronization, and camera accuracy, reducing rotation error by 30-65% and translation error by 61-72% relative to leading baselines. Project page is available at this https URL: https://qjizhi.github.io/track2view

Problem

• video re-rendering
• camera-controlled generation
• 4D consistency
• view synthesis
• spatiotemporal correspondence

Innovation

• 4D-consistent video generation
• camera-controlled synthesis
• 3D point tracks
• spatiotemporal correspondence
• video diffusion transformer