paper-with-me

Papers

S2DNet: Learning Image Features for Accurate Sparse-to-Dense Matching

2020-08-01 · ECCV 2020 8 · Hugo Germain, Guillaume Bourmaud, Vincent Lepetit

Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms. While recent learning-based feature matching methods have shown promising results in providing robust correspondences under challenging conditions, they are often limited in terms of precision. In this paper, we introduce S2DNet, a novel feature matching pipeline, designed and trained to efficiently establish both robust and accurate correspondences. By leveraging a sparse-to-dense matching paradigm, we cast the correspondence learning problem as a supervised classification task to learn to output highly peaked correspondence maps. We show that S2DNet achieves state-of-the-art results on the HPatches benchmark, as well as on several long-term visual localization datasets.

📄 PDF Abstract BibTeX

Code (3)

MindCode-4/code-13/tree/main/S2DNet-Minimal mindspore
MindCode-4/code-9/tree/main/S2DNet-Minimal mindspore
germain-hug/S2DNet-Minimal pytorch

Tasks

Visual Localization

Similar Papers 제목 키워드 기반

S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching

2020-04-03 · Hugo Germain, Guillaume Bourmaud, Vincent Lepetit

Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms. While recent learning-based feature matching methods have shown promising results in providing robust corresp…

Visual Localization

SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection

2024-03-09 · CVPR 2024 1 · Gang Zhang, Junnan Chen, Guohuan Gao, Jianmin Li 외

LiDAR-based 3D object detection plays an essential role in autonomous driving. Existing high-performing 3D object detectors usually build dense feature maps in the backbone network and prediction head. However, the compu…

3D Object DetectionAutonomous DrivingObjectobject-detection+1

BIRDNet: Mining and Encoding Boolean Implication Knowledge Graphs as Interpretable Deep Neural Networks

2026-05-27 · Tirtharaj Dash arxiv

Tabular data in knowledge-rich domains often carries a latent prior in the form of Boolean implication relationships (BIRs) between pairs of features. We mine such relationships with a sparse-exception binomial test. The…

Knowledge Graphs

EDFFDNet: Towards Accurate and Efficient Unsupervised Multi-Grid Image Registration

2025-09-09 · Haokai Zhu, Bo Qu, Si-Yuan Cao, Runmin Zhang 외 arxiv

Previous deep image registration methods that employ single homography, multi-grid homography, or thin-plate spline often struggle with real scenes containing depth disparities due to their inherent limitations. To addre…

Image Registration

RandNet: deep learning with compressed measurements of images

2019-08-25 · Thomas Chang, Bahareh Tolooshams, Demba Ba

Principal component analysis, dictionary learning, and auto-encoders are all unsupervised methods for learning representations from a large amount of training data. In all these methods, the higher the dimensions of the …

Deep LearningDictionary Learning