MSV-RGNN: MULTISCALE VOXEL GRAPH NEURAL NETWORK FOR 3D OBJECT DETECTION
Wonjoon Lee, Sungmin Woo, Donghyeong Kim, Sangyoun Lee
-
SPS
IEEE Members: $11.00
Non-members: $15.00
This paper proposes a two-stage 3D object detection framework, multiscale voxel graph neural network (MSV RGNN) which aims to fully exploit multiple scale graph fea tures by establishing global and local relationships between voxel features at different 3D convolutional neural network (CNN) layers. In contrast to conventional graph-based meth ods, our proposed multiscale-voxel-graph region-of-interest (RoI) pooling module constructs graphs across diverse voxel resolutions to obtain geometric structure information on voxel features. Initially, our multiscale-voxel-graph RoI pooling module sample voxel center points with voxel-wise feature vectors and 3D region proposals from backbone network. Subsequently, graphs are constructed at different scales and graph features are aggregated for second-stage refinement. The experimental results demonstrate the potential of using multiscale graphs across different voxel resolutions for 3D object detection, achieving decent experimental results with state-of-the-art methods.