Foundation4D unifies driving perception and 3D reconstruction
The model and PAI-Foundation4D benchmark cover 1,253 clips with dense depth and occupancy labels.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #3d-perception
Attention-DP3: Spatially Object-aware 3D Diffusion Policy via Geometry-aligned Attentional Conditioning
Attention-DP3 adds spatially object-aware attentional conditioning to 3D diffusion policies, improving robotic manipulation by up to 31% under heavy clutter.