FlashBEV: Fast and Memory-Efficient Exact BEV Transformation with IO-Awareness

arXiv:2607.10071v1 Announce Type: new Abstract: Bird's-eye-view (BEV) perception is a core component of camera-based 3D understanding in autonomous driving, where view transformation (VT) maps multi-camera image features into a unified BEV representation. Sampling-based view transformation (Sampling-VT) is attractive because it supports dense and continuous BEV aggregation for high-resolution and long-range perception. Its deployment bottleneck, however, is systems-level: standard tensorized imp...