HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras

arXiv:2404.02517v1 Announce Type: new
Abstract: Three-dimensional perception from multi-view cameras is a crucial component in autonomous driving systems, which involves multiple tasks like 3D object detection and bird's-eye-view (BEV) semantic segmentation. To improve perception precision, large image encoders, high-resolution images, and long-term temporal inputs have been adopted in recent 3D perception models, bringing remarkable performance gains. However, these techniques are often incompatible in training and inference scenarios due to computational resource constraints. Besides, modern autonomous driving systems prefer to adopt …

arxiv cameras cs.cv encoding hybrid perception type view