Deep Shape Matching

TL;DR

This paper introduces a deep learning approach for shape matching that leverages edge maps and metric learning, achieving state-of-the-art results across various tasks and domains.

Contribution

It presents a novel framework that combines traditional edge detection with deep metric learning, enabling versatile shape matching without task-specific models.

Findings

Improved performance on domain generalization tasks

State-of-the-art results in sketch-based image retrieval

Effective across multiple benchmarks

Abstract

We cast shape matching as metric learning with convolutional networks. We break the end-to-end process of image representation into two parts. Firstly, well established efficient methods are chosen to turn the images into edge maps. Secondly, the network is trained with edge maps of landmark images, which are automatically obtained by a structure-from-motion pipeline. The learned representation is evaluated on a range of different tasks, providing improvements on challenging cases of domain generalization, generic sketch-based image retrieval or its fine-grained counterpart. In contrast to other methods that learn a different model per task, object category, or domain, we use the same network throughout all our experiments, achieving state-of-the-art results in multiple benchmarks.