Put partial 3D point clouds into standard orientation with self-supervised ConDor
Put partial 3D point clouds into standard orientation with self-supervised ConDor
ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes
arXiv paper abstract https://arxiv.org/abs/2201.07788
arXiv PDF paper https://arxiv.org/pdf/2201.07788.pdf
Project page https://ivl.cs.brown.edu/ConDor
Progress in 3D object understanding has relied on manually canonicalized shape datasets that contain instances with consistent position and orientation (3D pose).
… ConDor is a self-supervised method that learns to Canonicalize the 3D orientation and position for full and partial 3D point clouds.
… build on top of Tensor Field Networks (TFNs) … method takes an unseen full or partial 3D point cloud at an arbitrary pose and outputs an equivariant canonical pose.
… network uses self-supervision losses to learn the canonical pose from an un-canonicalized collection of full and partial 3D point clouds.
ConDor can also learn to consistently co-segment object parts without any supervision.
… approach outperforms existing methods while enabling new applications such as operation on depth images and annotation transfer.
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
