Fully Sparse Fusion for 3D Object Detection
arxiv(2023)
摘要
Currently prevalent multimodal 3D detection methods are built upon
LiDAR-based detectors that usually use dense Bird's-Eye-View (BEV) feature
maps. However, the cost of such BEV feature maps is quadratic to the detection
range, making it not suitable for long-range detection. Fully sparse
architecture is gaining attention as they are highly efficient in long-range
perception. In this paper, we study how to effectively leverage image modality
in the emerging fully sparse architecture. Particularly, utilizing instance
queries, our framework integrates the well-studied 2D instance segmentation
into the LiDAR side, which is parallel to the 3D instance segmentation part in
the fully sparse detector. This design achieves a uniform query-based fusion
framework in both the 2D and 3D sides while maintaining the fully sparse
characteristic. Extensive experiments showcase state-of-the-art results on the
widely used nuScenes dataset and the long-range Argoverse 2 dataset. Notably,
the inference speed of the proposed method under the long-range LiDAR
perception setting is 2.7 × faster than that of other state-of-the-art
multimodal 3D detection methods. Code will be released at
.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要