SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.05777 · 2020

HDD-Net: Hybrid Detector Descriptor with Mutual Interactive Learning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Local feature extraction remains an active research area due to the advances in fields such as SLAM, 3D reconstructions, or AR applications. The success in these applications relies on the performance of the feature detector and descriptor. While the detector-descriptor interaction of most methods is based on unifying in single network detections and descriptors, we propose a method that treats both extractions independently and focuses on their interaction in the learning process rather than by parameter sharing. We formulate the classical hard-mining triplet loss as a new detector optimisation term to refine candidate positions based on the descriptor map. We propose a dense descriptor that uses a multi-scale approach and a hybrid combination of hand-crafted and learned features to obtain rotation and scale robustness by design. We evaluate our method extensively on different benchmarks and show improvements over the state of the art in terms of image matching on HPatches and 3D reconstruction quality while keeping on par on camera localisation tasks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2005.05777")
get_code_for_paper("2005.05777")
have("2005.05777")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2005.05777.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2005.05777.svg)](https://syntology.ai/paper/2005.05777)

Connect an agent — have() is free.