Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation

Marie Julie Rakotosaona, Maks Ovsjanikov

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

Abstract

We present a learning-based method for interpolating and manipulating 3D shapes represented as point clouds, that is explicitly designed to preserve intrinsic shape properties. Our approach is based on constructing a dual encoding space that enables shape synthesis and, at the same time, provides links to the intrinsic shape information, which is typically not available on point cloud data. Our method works in a single pass and avoids expensive optimization, employed by existing techniques. Furthermore, the strong regularization provided by our dual latent space approach also helps to improve shape recovery in challenging settings from noisy point clouds across different datasets. Extensive experiments show that our method results in more realistic and smoother interpolations compared to baselines. Both the code and our pre-trained network can be found online: https://github.com/mrakotosaon/intrinsic_interpolations.
Original languageEnglish (US)
Title of host publicationComputer Vision – ECCV 2020
PublisherSpringer International Publishing
Pages655-672
Number of pages18
ISBN (Print)9783030585358
DOIs
StatePublished - Nov 3 2020
Externally publishedYes

Fingerprint

Dive into the research topics of 'Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation'. Together they form a unique fingerprint.

Cite this