Search Results for author:
Found 3 papers, 1 papers with code
PBP-Net: Point Projection and Back-Projection Network for 3D Point Cloud Segmentation
In this paper, we propose a simple and efficient architecture named point projection and back-projection network (PBP-Net), which leverages 2D CNNs for the 3D point cloud segmentation.
Projection-based Point Convolution for Efficient Point Cloud Segmentation
Point branch consists of MLPs, while projection branch transforms point features into a 2D feature map and then apply 2D convolutions.
FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection
Compared to state-of-the-art methods, our proposed method delivers comparable performance on DOTA-v1. 0 and outperforms by 1. 5 mAP on DOTA-v1. 5, all while significantly reducing the model parameters to 16%.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
