computer-vision-11

Geometric 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 geometric-matching-11

Trend

Dataset

Best Model

Actions

HPatches

Libraries

i

Use these libraries to find geometric-matching-11 models and implementations

PruneTruong/DenseMatching

2 papers 614

Datasets

HPatches

Subtasks

No subtasks available.

Most implemented papers

Convolutional Neural Network Architecture for Geometric Matching

Josef Sivic, Ignacio Rocco, Relja Arandjelović•Wed Mar 15 2017

This work proposes a convolutional neural network architecture for geometric matching based on three main components that mimic the standard steps of feature extraction, matching and simultaneous inlier detection and model parameter estimation, while being trainable end-to-end.

575

Content

0

Paper Graph

Toward Characteristic-Preserving Image-based Virtual Try-On Network

Liang Lin, Xiaodan Liang, Yimin Chen, Bochao Wang, Huabing Zhang, Meng Yang•Thu Jul 19 2018

A new fully-learnable Characteristic-Preserving Virtual Try-On Network (CP-VTON) for addressing all real-world challenges in this task, and achieves the state-of-the-art virtual try-on performance both qualitatively and quantitatively.

454 0

Paper Graph

Learning Accurate Dense Correspondences and When to Trust Them

L. Gool, Martin Danelljan, Radu Timofte, Prune Truong•Mon Jan 04 2021

This work aims to estimate a dense flow field relating two images, coupled with a robust pixel-wise confidence map indicating the reliability and accuracy of the prediction, and develops a flexible probabilistic approach that jointly learns the flow prediction and its uncertainty.

155 0

Paper Graph

GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences

Martin Danelljan, Radu Timofte, Prune Truong•Tue Dec 10 2019

This work proposes a universal network architecture that is directly applicable to all the aforementioned dense correspondence problems, and achieves both high accuracy and robustness to large displacements by investigating the combined use of global and local correlation layers.

228 0

Paper Graph

GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network

L. Gool, Martin Danelljan, Radu Timofte, Prune Truong•Tue Sep 15 2020

The proposed GOCor module is a fully differentiable dense matching module, acting as a direct replacement to the feature correlation layer, capable of effectively learning spatial matching priors to resolve further matching ambiguities.

84 0

Paper Graph

Correlation Verification for Image Retrieval

Seongwon Lee, Hongje Seong, Suhyeon Lee, Euntai Kim•Sun Apr 03 2022

A novel image retrieval re-ranking network named Correlation Verification Networks (CVNet), comprising deeply stacked 4D convolutional layers, gradually compresses dense feature correlation into image similarity while learning diverse geometric matching patterns from various image pairs to enable cross-scale matching.

65 0

Paper Graph

C-VTON: Context-Driven Image-Based Virtual Try-On Network

Benjamin Fele, Ajda Lampe, P. Peer, Vitomir Štruc•Fri Dec 31 2021

Experimental results show that the proposed C-VTON approach is able to produce photo-realistic and visually convincing results and significantly improves on the existing state-of-the-art techniques.

66 0

Paper Graph

ContextDesc: Local Descriptor Augmentation With Cross-Modality Context

Yao Yao, Zixin Luo, Shiwei Li, Lei Zhou, Tian Fang, Long Quan, Tianwei Shen, Jiahui Zhang•Sun Apr 07 2019

This paper proposes a unified learning framework that leverages and aggregates the cross-modality contextual information, including visual context from high-level image representation, and geometric context from 2D keypoint distribution, and proposes an effective N-pair loss that eschews the empirical hyper-parameter search and improves the convergence.

235 0

Paper Graph

Self-Supervised 3D Keypoint Learning for Ego-motion Estimation

Adrien Gaidon, Rares Ambrus, V. Guizilini, Sudeep Pillai, Jiexiong Tang, Hanme Kim•Fri Dec 06 2019

This work proposes a fully self-supervised approach towards learning depth-aware keypoints from unlabeled videos by incorporating a differentiable pose estimation module that jointly optimizes the keypoints and their depths in a Structure-from-Motion setting.

23 0

Paper Graph

Adding a benchmark result helps the community track progress.