HIGHLIGHTS
- who: Xiaorui Zhang from the School of Computer and Software, Nanjing University of Information and Technology, Nanjing, China have published the research: 3D Object Detection with Attention: Shell-Based Modeling, in the Journal: (JOURNAL)
- what: To address the issues above this study proposes a new two-stage network structure to extract point cloud features directly by PointNet++ which effectively preserves the original point cloud coordinate information. The authors design a point-attention module adapted to 3D object detection between the encoder and decoder and creatively introduce the skip connection structure , where the network is backpropagating . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.