Deep Active Surface Models

TL;DR

This paper introduces Deep Active Surface Models that integrate active surface layers into Graph Convolutional Networks, enabling improved 3D surface reconstruction and segmentation by enforcing smoothness priors more effectively.

Contribution

It presents a novel integration of active surface layers into deep networks, enhancing 3D modeling capabilities with sophisticated smoothness priors.

Findings

Outperform traditional regularization methods in 3D surface reconstruction.

Effective integration of active surface layers into GCNs.

Improved 3D volume segmentation results.

Abstract

Active Surface Models have a long history of being useful to model complex 3D surfaces but only Active Contours have been used in conjunction with deep networks, and then only to produce the data term as well as meta-parameter maps controlling them. In this paper, we advocate a much tighter integration. We introduce layers that implement them that can be integrated seamlessly into Graph Convolutional Networks to enforce sophisticated smoothness priors at an acceptable computational cost. We will show that the resulting Deep Active Surface Models outperform equivalent architectures that use traditional regularization loss terms to impose smoothness priors for 3D surface reconstruction from 2D images and for 3D volume segmentation.