CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds

by   Yiming Zeng, et al.

This paper addresses the problem of computing dense correspondence between 3D shapes in the form of point clouds, which is a challenging and fundamental problem in computer vision and digital geometry processing. Conventional approaches often solve the problem in a supervised manner, requiring massive annotated data, which is difficult and/or expensive to obtain. Motivated by the intuition that one can transform two aligned point clouds to each other more easily and meaningfully than a misaligned pair, we propose CorrNet3D – the first unsupervised and end-to-end deep learning-based framework – to drive the learning of dense correspondence by means of deformation-like reconstruction to overcome the need for annotated data. Specifically, CorrNet3D consists of a deep feature embedding module and two novel modules called correspondence indicator and symmetric deformation. Feeding a pair of raw point clouds, our model first learns the pointwise features and passes them into the indicator to generate a learnable correspondence matrix used to permute the input pair. The symmetric deformer, with an additional regularized loss, transforms the two permuted point clouds to each other to drive the unsupervised learning of the correspondence. The extensive experiments on both synthetic and real-world datasets of rigid and non-rigid 3D shapes show our CorrNet3D outperforms state-of-the-art methods to a large extent, including those taking meshes as input. CorrNet3D is a flexible framework in that it can be easily adapted to supervised learning if annotated data are available.


page 3

page 8

page 13

page 15

page 16

page 17


Deep Magnification-Arbitrary Upsampling over 3D Point Clouds

This paper addresses the problem of generating dense point clouds from g...

Searching Dense Point Correspondences via Permutation Matrix Learning

Although 3D point cloud data has received widespread attentions as a gen...

RANSIP : From noisy point clouds to complete ear models, unsupervised

Ears are a particularly difficult region of the human face to model, not...

Point2SSM: Learning Morphological Variations of Anatomies from Point Cloud

We introduce Point2SSM, a novel unsupervised learning approach that can ...

RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut 2^D-Tree Representation

We propose RPSRNet - a novel end-to-end trainable deep neural network fo...

DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction

We present a new method for real-time non-rigid dense correspondence bet...

Deep Weighted Consensus: Dense correspondence confidence maps for 3D shape registration

We present a new paradigm for rigid alignment between point clouds based...

Please sign up or login with your details

Forgot password? Click here to reset