Saved in:
Bibliographic Details
Main Authors: Jiao, Yining, Zdanski, Carlton, Kimbell, Julia, Prince, Andrew, Worden, Cameron, Kirse, Samuel, Rutter, Christopher, Shields, Benjamin, Dunn, William, Mahmud, Jisan, Niethammer, Marc
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2303.09234
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909137378476032
author Jiao, Yining
Zdanski, Carlton
Kimbell, Julia
Prince, Andrew
Worden, Cameron
Kirse, Samuel
Rutter, Christopher
Shields, Benjamin
Dunn, William
Mahmud, Jisan
Niethammer, Marc
author_facet Jiao, Yining
Zdanski, Carlton
Kimbell, Julia
Prince, Andrew
Worden, Cameron
Kirse, Samuel
Rutter, Christopher
Shields, Benjamin
Dunn, William
Mahmud, Jisan
Niethammer, Marc
contents Deep implicit functions (DIFs) have emerged as a powerful paradigm for many computer vision tasks such as 3D shape reconstruction, generation, registration, completion, editing, and understanding. However, given a set of 3D shapes with associated covariates there is at present no shape representation method which allows to precisely represent the shapes while capturing the individual dependencies on each covariate. Such a method would be of high utility to researchers to discover knowledge hidden in a population of shapes. For scientific shape discovery, we propose a 3D Neural Additive Model for Interpretable Shape Representation ($\texttt{NAISR}$) which describes individual shapes by deforming a shape atlas in accordance to the effect of disentangled covariates. Our approach captures shape population trends and allows for patient-specific predictions through shape transfer. $\texttt{NAISR}$ is the first approach to combine the benefits of deep implicit shape representations with an atlas deforming according to specified covariates. We evaluate $\texttt{NAISR}$ with respect to shape reconstruction, shape disentanglement, shape evolution, and shape transfer on three datasets: 1) $\textit{Starman}$, a simulated 2D shape dataset; 2) the ADNI hippocampus 3D shape dataset; and 3) a pediatric airway 3D shape dataset. Our experiments demonstrate that $\textit{Starman}$ achieves excellent shape reconstruction performance while retaining interpretability. Our code is available at $\href{https://github.com/uncbiag/NAISR}{https://github.com/uncbiag/NAISR}$.
format Preprint
id arxiv_https___arxiv_org_abs_2303_09234
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle NAISR: A 3D Neural Additive Model for Interpretable Shape Representation
Jiao, Yining
Zdanski, Carlton
Kimbell, Julia
Prince, Andrew
Worden, Cameron
Kirse, Samuel
Rutter, Christopher
Shields, Benjamin
Dunn, William
Mahmud, Jisan
Niethammer, Marc
Computer Vision and Pattern Recognition
Deep implicit functions (DIFs) have emerged as a powerful paradigm for many computer vision tasks such as 3D shape reconstruction, generation, registration, completion, editing, and understanding. However, given a set of 3D shapes with associated covariates there is at present no shape representation method which allows to precisely represent the shapes while capturing the individual dependencies on each covariate. Such a method would be of high utility to researchers to discover knowledge hidden in a population of shapes. For scientific shape discovery, we propose a 3D Neural Additive Model for Interpretable Shape Representation ($\texttt{NAISR}$) which describes individual shapes by deforming a shape atlas in accordance to the effect of disentangled covariates. Our approach captures shape population trends and allows for patient-specific predictions through shape transfer. $\texttt{NAISR}$ is the first approach to combine the benefits of deep implicit shape representations with an atlas deforming according to specified covariates. We evaluate $\texttt{NAISR}$ with respect to shape reconstruction, shape disentanglement, shape evolution, and shape transfer on three datasets: 1) $\textit{Starman}$, a simulated 2D shape dataset; 2) the ADNI hippocampus 3D shape dataset; and 3) a pediatric airway 3D shape dataset. Our experiments demonstrate that $\textit{Starman}$ achieves excellent shape reconstruction performance while retaining interpretability. Our code is available at $\href{https://github.com/uncbiag/NAISR}{https://github.com/uncbiag/NAISR}$.
title NAISR: A 3D Neural Additive Model for Interpretable Shape Representation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2303.09234