Instance-aware Multi-Camera 3D Object Detection with Structural Priors Mining and Self-Boosting Learning
원문 초록
Camera-based bird-eye-view (BEV) perception paradigm has made significant progress in the autonomous driving field. Under such a paradigm, accurate BEV representation construction relies on reliable depth estimation for multi-camera images. However, existing approaches exhaustively predict depths for every pixel without prioritizing objects, which are precisely the entities requiring detection in the 3D space. To this end, we propose IA-BEV, which integrates image-plane instance awareness into the depth estimation process within a BEV-based detector. First, a category-specific structural priors mining approach is proposed for enhancing the efficacy of monocular depth generation. Besides, a self-boosting learning strategy is further proposed to encourage the model to place more emphasis on challenging objects in computation-expensive temporal stereo matching. Together they provide advanced depth estimation results for high-quality BEV features construction, benefiting the ultimate 3D detection. The proposed method achieves state-of-the-art performances on the challenging nuScenes benchmark, and extensive experimental results demonstrate the effectiveness of our designs.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations
A Survey of Multi-sensor Fusion Perception for Embodied AI: Background, Methods, Challenges and Prospects
Teleoperated Driving: a New Challenge for 3D Object Detection in Compressed Point Clouds
Vision-based Lifting of 2D Object Detections for Automated Driving
DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videos
SpikeSMOKE: Spiking Neural Networks for Monocular 3D Object Detection with Cross-Scale Gated Coding
토론
이 논문과 연결된 포럼 글이 아직 없습니다.