# Topology Maintained Structure Encoding

## TL;DR

This paper introduces a Voronoi Diagram encoder based on convex set distance that preserves topological properties like connection structures and contours, improving edge detection and structure generation in CNNs and GANs.

## Contribution

The paper proposes a novel Voronoi Diagram encoder that maintains topological features, enhancing contour extraction and structure modeling in deep learning.

## Key findings

- Improves contour extraction accuracy in CNNs.
- Enhances structure generation in GANs.
- Demonstrates potential in topology-aware visual tasks.

## Abstract

Deep learning has been used as a powerful tool for various tasks in computer vision, such as image segmentation, object recognition and data generation. A key part of end-to-end training is designing the appropriate encoder to extract specific features from the input data. However, few encoders maintain the topological properties of data, such as connection structures and global contours. In this paper, we introduce a Voronoi Diagram encoder based on convex set distance (CSVD) and apply it in edge encoding. The boundaries of Voronoi cells is related to detected edges of structures and contours. The CSVD model improves contour extraction in CNN and structure generation in GAN. We also show the experimental results and demonstrate that the proposed model has great potentiality in different visual problems where topology information should be involved.