Placeholder chapter page. Sections are produced by the book-skills pipeline.
Sections
- 43.1 Bird's-eye-view as a shared representation
- 43.2 Camera-to-BEV lifting and BEVFormer-style attention
- 43.3 BEV multi-sensor fusion (BEVFusion)
- 43.4 3D semantic occupancy prediction (Occ3D, SurroundOcc, TPVFormer)
- 43.5 Self-supervised and Gaussian occupancy (GaussianOcc)
- 43.6 Occupancy world models (developed further in Ch 53)
- 43.7 Benchmarks and metrics
Lab 43
train a BEV or occupancy model on an Occ3D benchmark subset; evaluate under a missing-sensor condition.