computer-vision
3D Canonicalization
3260 papers • 126 benchmarks • 313 datasets
3D Canonicalization is the process of estimating a transformation-invariant feature for classification and part segmentation tasks.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in 3d-canonicalization
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find 3d-canonicalization models and implementations
Datasets
No datasets available.
Subtasks
No subtasks available.
Most implemented papers
ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes
L. Guibas, Srinath Sridhar, Rahul Sajnani, A. Poulenard, Jivitesh Jain, Radhika Dua•Tue Jan 18 2022
ConDor is a self-supervised method that learns to Canonicalize the 3D orientation and position for full and partial 3D point clouds on top of Tensor Field Networks, a class of permutation- and rotation-equivariant, and translation-invariant 3D networks.
43