Image Matching

11 papers with code • 1 benchmarks • 1 datasets

Image Matching or wide multiple baseline stereo (WxBS) is a process of establishing a sufficient number of pixel or region correspondences from two or more images depicting the same scene to estimate the geometric relationship between cameras, which produced these images.

Source: The Role of Wide Baseline Stereo in the Deep Learning World

( Image credit: Kornia )

Most implemented papers

SuperGlue: Learning Feature Matching with Graph Neural Networks

magicleap/SuperGluePretrainedNetwork CVPR 2020

This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points.

What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis

clovaai/deep-text-recognition-benchmark ICCV 2019

Many new proposals for scene text recognition (STR) models have been introduced in recent years.

Kornia: an Open Source Differentiable Computer Vision Library for PyTorch

kornia/kornia 5 Oct 2019

This work presents Kornia -- an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems.

Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters

axelBarroso/Key.Net ICCV 2019

We introduce a novel approach for keypoint detection task that combines handcrafted and learned CNN filters within a shallow multi-scale architecture.

D2-Net: A Trainable CNN for Joint Detection and Description of Local Features

mihaidusmanu/d2-net 9 May 2019

In this work we address the problem of finding reliable pixel-level correspondences under difficult imaging conditions.

LoFTR: Detector-Free Local Feature Matching with Transformers

zju3dv/LoFTR CVPR 2021

We present a novel method for local image feature matching.

Three things everyone should know to improve object retrieval

ubc-vision/image-matching-benchmark CVPR 2012

The objective of this work is object retrieval in large scale image datasets, where the object is specified by an image query and retrieval should be immediate at run time in the manner of Video Google [28].

R2D2: Reliable and Repeatable Detector and Descriptor

naver/r2d2 NeurIPS 2019

We thus propose to jointly learn keypoint detection and description together with a predictor of the local descriptor discriminativeness.

DISK: Learning local features with policy gradient

cvlab-epfl/disk NeurIPS 2020

Local feature frameworks are difficult to learn in an end-to-end fashion, due to the discreteness inherent to the selection and matching of sparse keypoints.