Foundation4D: Towards a unified perception and reconstruction model for autonomous vehicles
arXiv:2610.30340v1 Announce Type: new Abstract: We introduce Foundation4D, a unified feed-forward model for geometry estimation, 3D detection, semantic occupancy, and Gaussian reconstruction from multi-camera driving video. A shared backbone uses factorized spatiotemporal attention to efficiently c…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-23 04:00 · arXiv cs.CV
Foundation4D: Towards a unified perception and reconstruction model for autonomous vehicles