CLIP-BEVFormer: Enhancing Multi-View Image-Based BEV Detector with Ground Truth Flow
원문 초록
Autonomous driving stands as a pivotal domain in computer vision, shaping the future of transportation. Within this paradigm, the backbone of the system plays a crucial role in interpreting the complex environment. However, a notable challenge has been the loss of clear supervision when it comes to Bird's Eye View elements. To address this limitation, we introduce CLIP-BEVFormer, a novel approach that leverages the power of contrastive learning techniques to enhance the multi-view image-derived BEV backbones with ground truth information flow. We conduct extensive experiments on the challenging nuScenes dataset and showcase significant and consistent improvements over the SOTA. Specifically, CLIP-BEVFormer achieves an impressive 8.5\% and 9.2\% enhancement in terms of NDS and mAP, respectively, over the previous best BEV model on the 3D object detection task.
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
Snow Removal for LiDAR Point Clouds with Spatio-temporal Conditional Random Fields
RCFusion: Fusing 4-D Radar and Camera With Bird’s-Eye View Features for 3-D Object Detection
토론
이 논문과 연결된 포럼 글이 아직 없습니다.