Deep Neural Network for 3D Surface Segmentation based on Contour Tree Hierarchy

TL;DR

This paper introduces a novel graph neural network that leverages contour tree hierarchies to improve 3D surface segmentation, effectively capturing topological features across multiple scales.

Contribution

It proposes a contour tree-based representation and a specialized graph neural network for surface segmentation, addressing limitations of traditional image-based models.

Findings

Outperforms baseline methods in classification accuracy on hydrological datasets.

Effectively captures multi-scale surface topological structures.

Demonstrates applicability to real-world 3D surface analysis.

Abstract

Given a 3D surface defined by an elevation function on a 2D grid as well as non-spatial features observed at each pixel, the problem of surface segmentation aims to classify pixels into contiguous classes based on both non-spatial features and surface topology. The problem has important applications in hydrology, planetary science, and biochemistry but is uniquely challenging for several reasons. First, the spatial extent of class segments follows surface contours in the topological space, regardless of their spatial shapes and directions. Second, the topological structure exists in multiple spatial scales based on different surface resolutions. Existing widely successful deep learning models for image segmentation are often not applicable due to their reliance on convolution and pooling operations to learn regular structural patterns on a grid. In contrast, we propose to represent surface topological structure by a contour tree skeleton, which is a polytree capturing the evolution of surface contours at different elevation levels. We further design a graph neural network based on the contour tree hierarchy to model surface topological structure at different spatial scales. Experimental evaluations based on real-world hydrological datasets show that our model outperforms several baseline methods in classification accuracy.