Deep Active Latent Surfaces for Medical Geometries

Patrick M. Jensen, Udaranga Wickramasinghe, Anders B. Dahl, Pascal Fua, Vedrana A. Dahl

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

6 Downloads (Orbit)

Abstract

Shape priors have long been known to be effective when reconstructing 3D shapes from noisy or incomplete data. When using a deep-learning based shape representation, this often involves learning a latent representation, which can be either in the form of a single global vector or of multiple local ones. The latter allows more flexibility but is prone to overfitting. In this paper, we advocate a hybrid approach representing shapes in terms of 3D meshes with a separate latent vector at each vertex. During training the latent vectors are constrained to have the same value, which avoids overfitting. For inference, the latent vectors are updated independently while imposing spatial regularization constraints. We show that this gives us both flexibility and generalization capabilities, which we demonstrate on several medical image processing tasks.
Original languageEnglish
Title of host publicationProceedings of the 6th Northern Lights Deep Learning Conference (NLDL
Volume265
PublisherProceedings of Machine Learning Research
Publication date2025
Pages120-132
Publication statusPublished - 2025
Event6th Northern Lights Deep Learning Conference 2025 - Tromsø, Norway
Duration: 7 Jan 20259 Jan 2025

Conference

Conference6th Northern Lights Deep Learning Conference 2025
Country/TerritoryNorway
CityTromsø
Period07/01/202509/01/2025
SeriesProceedings of Machine Learning Research
ISSN2640-3498

Fingerprint

Dive into the research topics of 'Deep Active Latent Surfaces for Medical Geometries'. Together they form a unique fingerprint.

Cite this