MemDistill: Distilling LiDAR Knowledge into Memory for Camera-Only 3D Object Detection

Camera-based 3D object detection has gained attention for its cost-effectiveness, but it in general lags behind LiDARbased approaches due to its lack of explicit 3D spatial cues. To take the best of both camera-and LiDAR-based detectors, we propose MemDistill, a novel cross-modal knowledge distillation framework for 3D object detection. MemDistill transfers rich 3D knowledge from a LiDARbased teacher model to a camera-based student model through a dedicated memory unit and a scene-dependent memory retrieval module. To be specific, our framework distills the teacher's 3D knowledge, optimizes the memory to store that knowledge compactly, and learns the retriever that searches the memory to produce 3D features relevant to the input scene, compensating for the missing LiDAR modality. Experiments on the nuScenes dataset demonstrate that MemDistill significantly improves performance of its camera-only baseline, achieving the state of the art in camera-based 3D object detection.