Streaming Gaussian Encoding for 4D Panoptic Occupancy Tracking

arXiv:2606.30754v1 Announce Type: new Abstract: Camera-based 4D panoptic occupancy tracking (4D-POT) is a promising paradigm for holistic scene understanding from multi-view imagery, enabling joint reasoning about geometry, semantics, and object identities across time. Recent mask-based pipelines achieve strong performance by propagating instance queries across frames. However, their underlying volumetric representations are typically recomputed at each timestep, limiting geometric temporal cons...

arXiv cs.CV ·Maximilian Luz, Thomas N\"urnberg, Yakov Miron, Abhinav Valada ·
compartilhar: