ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers

arXiv:2405.04299v1 Announce Type: new
Abstract: 3D occupancy, an advanced perception technology for driving scenarios, represents the entire scene without distinguishing between foreground and background by quantifying the physical space into a grid map. The widely adopted projection-first deformable attention, efficient in transforming image features into 3D representations, encounters challenges in aggregating multi-view features due to sensor deployment constraints. To address this issue, we propose our learning-first view attention mechanism for effective multi-view feature aggregation. Moreover, we showcase the scalability of …

abstract advanced arxiv attention cs.cv driving features grid image map modeling perception projection space technology transformers type via view