cs.CV2026
VISA: VLM-Guided Instance Semantic Auditing for 3D Occupancy World Models
Ruiqi Xian, Yuehan Xian, Jing Liang +2
The paper introduces VISA, a training-time method that uses a visual‑language model to audit and correct semantic labels of 3D voxel occupancy maps, improving object and rare‑class…
#3d occupancy mapping#semantic auditing#visual language models#autonomous driving