Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

computer-vision-1

Patch Matching

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in patch-matching-1

Trend

Dataset

Best Model

Actions

HPatches

Brown Dataset

Libraries

Use these libraries to find patch-matching-1 models and implementations

Datasets

Subtasks

Multimodal Patch Matching

Most implemented papers

Working hard to know your neighbor's margins: Local descriptor learning loss

Dmytro Mishkin, Jiri Matas, Filip Radenovic, A. Mishchuk•Mon May 29 2017

A novel loss for learning local feature descriptors which is inspired by the Lowe's matching criterion for SIFT is introduced, and it is shown that the proposed loss that maximizes the distance between the closest positive and closest negative patch in the batch is better than complex regularization methods.

761

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Rotation Equivariant Vector Field Networks

D. Tuia, N. Komodakis, Diego Marcos, M. Volpi•Wed Dec 28 2016

The Rotation Equivariant Vector Field Networks (RotEqNet), a Convolutional Neural Network architecture encoding rotation equivariance, invariance and covariance, is proposed and a modified convolution operator relying on this representation to obtain deep architectures is developed.

284 0

Paper Graph

Distinctive Image Features from Scale-Invariant Keypoints

D. Lowe•Sun Oct 31 2004

This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.

49324 0

Paper Graph

Continuous 3D Label Stereo Matching Using Local Expansion Moves

Yoichi Sato, Tatsunori Taniai, Y. Matsushita, T. Naemura•Sun Mar 27 2016

This new move-making scheme is used to efficiently infer per-pixel 3D plane labels on a pairwise Markov random field (MRF) that effectively combines recently proposed slanted patch matching and curvature regularization terms.

156 0

Paper Graph

Attention Concatenation Volume for Accurate and Efficient Stereo Matching

Gangwei Xu, Junda Cheng, Peng Guo, Xin Yang•Thu Mar 03 2022

A novel cost volume construction method which generates attention weights from correlation clues to suppress redundant information and enhance matching-related information in the concatenation volume is presented.

269 0

Paper Graph

Person Re-Identification with Correspondence Structure Learning

Jingdong Wang, Jianxin Wu, Weiyao Lin, Junchi Yan, Mingliang Xu, Yang Shen•Wed Apr 22 2015

A boosting-based approach to learn a correspondence structure which indicates the patch-wise matching probabilities between images from a target camera pair is introduced, which integrates a global matching constraint over the learned correspondence structure to exclude cross-view misalignments during the image patch matching process, hence achieving a more reliable matching score between images.

174 0

Paper Graph

Deep Colorization

Zezhou Cheng, Qingxiong Yang, Bin Sheng•Sun Dec 06 2015

Inspired by the recent success in deep learning techniques which provide amazing modeling of large-scale data, this paper re-formulates the colorization problem so thatDeep learning techniques can be directly employed and a joint bilateral filtering based post-processing step is proposed to ensure artifact-free quality.

601 0

Paper Graph

Person Re-identification via Recurrent Feature Aggregation

Bingbing Ni, Yan Yan, Yichao Yan, Xiaokang Yang, Zhichao Song, Chao Ma•Fri Oct 07 2016

This work shows that a progressive/sequential fusion framework based on long short term memory (LSTM) network aggregates the frame-wise human region representation at each time stamp and yields a sequence level human feature representation.

250 0

Paper Graph

Adding a benchmark result helps the community track progress.

Patch Matching | State-of-the-Art