SOURCE-LINKED INTELLIGENCE

PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

World models endow perceptual systems with the ability to predict how scenes evolve under interaction. They are most beneficial when trained on diverse volumes of data, to instill a rich prior into downstream applications. Existing methods typically require robot action labels to learn action-conditioned 3D dynamics, which excludes web video data from the training pool. We study 3D point track completion as a pre-training objective for learning transferable 3D dynamics without robot data. Given a single RGB-D observation and sparse partial 3D trajectories (tracks), we predict future 3D tracks

Read original source ↗ Open in workspace

recordType

paper

region

Global