Multi-View Attentive Contextualization for Multi-View 3D Object Detection
CVPR 2024(2024)
摘要
We present Multi-View Attentive Contextualization (MvACon), a simple yet
effective method for improving 2D-to-3D feature lifting in query-based
multi-view 3D (MV3D) object detection. Despite remarkable progress witnessed in
the field of query-based MV3D object detection, prior art often suffers from
either the lack of exploiting high-resolution 2D features in dense
attention-based lifting, due to high computational costs, or from
insufficiently dense grounding of 3D queries to multi-scale 2D features in
sparse attention-based lifting. Our proposed MvACon hits the two birds with one
stone using a representationally dense yet computationally sparse attentive
feature contextualization scheme that is agnostic to specific 2D-to-3D feature
lifting approaches. In experiments, the proposed MvACon is thoroughly tested on
the nuScenes benchmark, using both the BEVFormer and its recent 3D deformable
attention (DFA3D) variant, as well as the PETR, showing consistent detection
performance improvement, especially in enhancing performance in location,
orientation, and velocity prediction. It is also tested on the Waymo-mini
benchmark using BEVFormer with similar improvement. We qualitatively and
quantitatively show that global cluster-based contexts effectively encode dense
scene-level contexts for MV3D object detection. The promising results of our
proposed MvACon reinforces the adage in computer vision – “(contextualized)
feature matters".
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