Reliable multi-view forecasting requires videos from different cameras to describe the same evolving 3D scene. To this end, we introduce Video-Point Model (VPM), a world model that conditions on multi-view video histories and a language instruction to jointly forecast future videos from arbitrary viewpoints and the 3D trajectories of persistent scene points.
ORIGINAL PAPER
Learning the 4D World through Point Trajectory Forecasting
WHAT WE KNOW
We extend a pretrained world model with camera-conditioned multi-view processing that integrates complementary observations across cameras, and add a trajectory head that predicts how physical points move through time. Each trajectory tracks a single point across all views, and supervising these trajectories alongside video generation therefore anchors appearance changes in every camera to a shared description of 3D motion.
WATCH NEXT
Review the primary source, validate the main result, and establish whether any listed-company transmission is direct.
EVIDENCE
What the evidence supports so far
Research signals
world-model
multimodal
What remains unverified
The full methodology, effect size, and limitations still require analyst review.
Company impact remains unverified until a direct economic transmission is established.