Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets

by   Clara Fernandez-Labrador, et al.

Automatic discovery of category-specific 3D keypoints from a collection of objects of some category is a challenging problem. One reason is that not all objects in a category necessarily have the same semantic parts. The level of difficulty adds up further when objects are represented by 3D point clouds, with variations in shape and unknown coordinate frames. We define keypoints to be category-specific, if they meaningfully represent objects' shape and their correspondences can be simply established order-wise across all objects. This paper aims at learning category-specific 3D keypoints, in an unsupervised manner, using a collection of misaligned 3D point clouds of objects from an unknown category. In order to do so, we model shapes defined by the keypoints, within a category, using the symmetric linear basis shapes without assuming the plane of symmetry to be known. The usage of symmetry prior leads us to learn stable keypoints suitable for higher misalignments. To the best of our knowledge, this is the first work on learning such keypoints directly from 3D point clouds. Using categories from four benchmark datasets, we demonstrate the quality of our learned keypoints by quantitative and qualitative evaluations. Our experiments also show that the keypoints discovered by our method are geometrically and semantically consistent.


Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstruction

Semantic 3D keypoints are category-level semantic consistent points on 3...

KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control

We introduce KeypointDeformer, a novel unsupervised method for shape con...

Do Time Constraints Re-Prioritize Attention to Shapes During Visual Photo Inspection?

People's visual experiences of the world are easy to carve up and examin...

Data-driven Upsampling of Point Clouds

High quality upsampling of sparse 3D point clouds is critically useful f...

Learned Interpolation for 3D Generation

In order to generate novel 3D shapes with machine learning, one must all...

SimNP: Learning Self-Similarity Priors Between Neural Points

Existing neural field representations for 3D object reconstruction eithe...

Unsupervised Learning of Shape and Pose with Differentiable Point Clouds

We address the problem of learning accurate 3D shape and camera pose fro...

Please sign up or login with your details

Forgot password? Click here to reset