Object-Level Reconstruction. Reconstructed shapes from the ModelNet10 test set using four different DSR methods trained on ModelNet10. Top rows of each object use the bare point cloud as input, and bottom rows use the point cloud augmented with visibility information.

Object-Level Reconstruction. Reconstructed shapes from the ModelNet10 test set using four different DSR methods trained on ModelNet10. Top rows of each object use the bare point cloud as input, and bottom rows use the point cloud augmented with visibility information.

Source publication
Preprint
Full-text available
Most current neural networks for reconstructing surfaces from point clouds ignore sensor poses and only operate on raw point locations. Sensor visibility, however, holds meaningful information regarding space occupancy and surface orientation. In this paper, we present two simple ways to augment raw point clouds with visibility information, so it c...

Context in source publication

Context 1
... of these strategies brought significant improvements over adding two points at distance d on both sides of the real point. Figure 3. ...

Similar publications

Article
Full-text available
To improve the detection ability of infrared small targets in complex backgrounds, an improved detection algorithm YOLO-SASE is proposed in this paper. The algorithm is based on the YOLO detection framework and SRGAN network, taking super-resolution reconstructed images as input, combined with the SASE module, SPP module, and multi-level receptive...