Adjoint Rigid Transform Network: Self-supervised Alignment of 3D Shapes

by   Keyang Zhou, et al.

Most learning methods for 3D data (point clouds, meshes) suffer significant performance drops when the data is not carefully aligned to a canonical orientation. Aligning real world 3D data collected from different sources is non-trivial and requires manual intervention. In this paper, we propose the Adjoint Rigid Transform (ART) Network, a neural module which can be integrated with existing 3D networks to significantly boost their performance in tasks such as shape reconstruction, non-rigid registration, and latent disentanglement. ART learns to rotate input shapes to a canonical orientation that is crucial for a lot of tasks. ART achieves this by imposing rotation equivariance constraint on input shapes. The remarkable result is that with only self-supervision, ART can discover a unique canonical orientation for both rigid and nonrigid objects, which leads to a notable boost in downstream task performance. We will release our code and pre-trained models for further research.


page 5

page 6

page 8


ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes

Progress in 3D object understanding has relied on manually canonicalized...

Learning to Orient Surfaces by Self-supervised Spherical CNNs

Defining and reliably finding a canonical orientation for 3D surfaces is...

Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matching

The matching of 3D shapes has been extensively studied for shapes repres...

PointGMM: a Neural GMM Network for Point Clouds

Point clouds are a popular representation for 3D shapes. However, they e...

Learning Canonical Embedding for Non-rigid Shape Matching

This paper provides a novel framework that learns canonical embeddings f...

Shape Registration with Directional Data

We propose several cost functions for registration of shapes encoded wit...

Deep Confidence Guided Distance for 3D Partial Shape Registration

We present a novel non-iterative learnable method for partial-to-partial...

Please sign up or login with your details

Forgot password? Click here to reset