|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
3D point cloud completion, the task of inferring the complete geometric shape from a partial point cloud, has been attracting attention in the community.
Ranked #3 on Point Cloud Completion on ShapeNet
Unlike existing point cloud completion networks, which generate the overall shape of the point cloud from the incomplete point cloud and always change existing points and encounter noise and geometrical loss, PF-Net preserves the spatial arrangements of the incomplete point cloud and can figure out the detailed geometrical structure of the missing region(s) in the prediction.
In particular, we devise two novel differentiable layers, named Gridding and Gridding Reverse, to convert between point clouds and 3D grids without losing structural information.
Ranked #1 on Point Cloud Completion on Completion3D
As 3D scanning solutions become increasingly popular, several deep learning setups have been developed geared towards that task of scan completion, i. e., plausibly filling in regions there were missed in the raw scans.
In this paper, we propose a method for 3D object completion and classification based on point clouds.
In view of these, we propose a self-supervised object completion method, which optimizes the training procedure solely on the partial input without utilizing the fully-complete ground truth.