MTLDesc: Looking Wider to Describe Better

03/14/2022
by   Changwei Wang, et al.
0

Limited by the locality of convolutional neural networks, most existing local features description methods only learn local descriptors with local information and lack awareness of global and surrounding spatial context. In this work, we focus on making local descriptors "look wider to describe better" by learning local Descriptors with More Than just Local information (MTLDesc). Specifically, we resort to context augmentation and spatial attention mechanisms to make our MTLDesc obtain non-local awareness. First, Adaptive Global Context Augmented Module and Diverse Local Context Augmented Module are proposed to construct robust local descriptors with context information from global to local. Second, Consistent Attention Weighted Triplet Loss is designed to integrate spatial attention awareness into both optimization and matching stages of local descriptors learning. Third, Local Features Detection with Feature Pyramid is given to obtain more stable and accurate keypoints localization. With the above innovations, the performance of our MTLDesc significantly surpasses the prior state-of-the-art local descriptors on HPatches, Aachen Day-Night localization and InLoc indoor localization benchmarks.

READ FULL TEXT

page 1

page 3

page 4

research
09/13/2020

TCDesc: Learning Topology Consistent Descriptors for Image Matching

The constraint of neighborhood consistency or local consistency is widel...
research
09/23/2020

Leveraging Local and Global Descriptors in Parallel to Search Correspondences for Visual Localization

Visual localization to compute 6DoF camera pose from a given image has w...
research
04/08/2019

ContextDesc: Local Descriptor Augmentation with Cross-Modality Context

Most existing studies on learning local features focus on the patch-base...
research
03/23/2020

ASLFeat: Learning Local Features of Accurate Shape and Localization

This work focuses on mitigating two limitations in the joint learning of...
research
04/19/2022

OpenGlue: Open Source Graph Neural Net Based Pipeline for Image Matching

We present OpenGlue: a free open-source framework for image matching, th...
research
02/25/2020

Ground Texture Based Localization Using Compact Binary Descriptors

Ground texture based localization is a promising approach to achieve hig...
research
05/31/2018

Accurate pedestrian localization in overhead depth images via Height-Augmented HOG

We tackle the challenge of reliably and automatically localizing pedestr...

Please sign up or login with your details

Forgot password? Click here to reset