2025-01-12-jensen25a.md

title	openreview	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Deep Active Latent Surfaces for Medical Geometries	TP0ASAlrp2	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.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	jensen25a	0	Deep Active Latent Surfaces for Medical Geometries	120	132	120-132	120	false	Jensen, Patrick M{\o}ller and Wickramasinghe, Udaranga and Dahl, Anders and Fua, Pascal and Dahl, Vedrana Andersen	given family Patrick Møller Jensen given family Udaranga Wickramasinghe given family Anders Dahl given family Pascal Fua given family Vedrana Andersen Dahl	2025-01-12		Proceedings of the 6th Northern Lights Deep Learning Conference (NLDL)	265	inproceedings	date-parts 2025 1 12	https://raw.githubusercontent.com/mlresearch/v265/main/assets/jensen25a/jensen25a.pdf