DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction

TL;DR

DPC introduces a real-time, unsupervised method for non-rigid dense point cloud correspondence that outperforms existing approaches by avoiding the decoder and requiring less training data.

Contribution

It proposes a novel decoder-free approach using shape construction and latent similarity, improving generalization and efficiency in dense point correspondence.

Findings

Outperforms recent state-of-the-art methods

Requires less training data and achieves better generalization

Operates in real-time without a decoder component

Abstract

We present a new method for real-time non-rigid dense correspondence between point clouds based on structured shape construction. Our method, termed Deep Point Correspondence (DPC), requires a fraction of the training data compared to previous techniques and presents better generalization capabilities. Until now, two main approaches have been suggested for the dense correspondence problem. The first is a spectral-based approach that obtains great results on synthetic datasets but requires mesh connectivity of the shapes and long inference processing time while being unstable in real-world scenarios. The second is a spatial approach that uses an encoder-decoder framework to regress an ordered point cloud for the matching alignment from an irregular input. Unfortunately, the decoder brings considerable disadvantages, as it requires a large amount of training data and struggles to generalize well in cross-dataset evaluations. DPC's novelty lies in its lack of a decoder component. Instead, we use latent similarity and the input coordinates themselves to construct the point cloud and determine correspondence, replacing the coordinate regression done by the decoder. Extensive experiments show that our construction scheme leads to a performance boost in comparison to recent state-of-the-art correspondence methods. Our code is publicly available at https://github.com/dvirginz/DPC.