Unsupervised deep learning for structured shape matching

Jean Michel Roufosse, Abhishek Sharma, Maks Ovsjanikov

Research output: Chapter in Book/Report/Conference proceedingConference contribution

44 Scopus citations

Abstract

We present a novel method for computing correspondences across 3D shapes using unsupervised learning. Our method computes a non-linear transformation of given descriptor functions, while optimizing for global structural properties of the resulting maps, such as their bijectivity or approximate isometry. To this end, we use the functional maps framework, and build upon the recent FMNet architecture for descriptor learning. Unlike that approach, however, we show that learning can be done in a purely emph{unsupervised setting}, without having access to any ground truth correspondences. This results in a very general shape matching method that we call SURFMNet for Spectral Unsupervised FMNet, and which can be used to establish correspondences within 3D shape collections without any prior information. We demonstrate on a wide range of challenging benchmarks, that our approach leads to state-of-the-art results compared to the existing unsupervised methods and achieves results that are comparable even to the supervised learning techniques. Moreover, our framework is an order of magnitude faster, and does not rely on geodesic distance computation or expensive post-processing.
Original languageEnglish (US)
Title of host publication2019 IEEE/CVF International Conference on Computer Vision (ICCV)
PublisherIEEE
Pages1617-1627
Number of pages11
ISBN (Print)9781728148038
DOIs
StatePublished - Feb 27 2020
Externally publishedYes

Fingerprint

Dive into the research topics of 'Unsupervised deep learning for structured shape matching'. Together they form a unique fingerprint.

Cite this