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

© 2026 Papersgraph. All rights reserved.

computer-vision

Visual Localization

3260 papers • 126 benchmarks • 313 datasets

Visual Localization is the problem of estimating the camera pose of a given image relative to a visual representation of a known scene. Source: Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in visual-localization

Trend

Dataset

Best Model

Actions

Oxford Radar RobotCar (Full-6)

Oxford Radar RobotCar (Full-6)

Oxford RobotCar Full

Oxford RobotCar Full

Libraries

i

Use these libraries to find visual-localization models and implementations

naver/kapture-localization

3 papers 255

Datasets

NCLT

Cambridge Landmarks

Cambridge Landmarks

Aachen Day-Night

Aachen Day-Night

InLoc

KAIST Urban

Subtasks

No subtasks available.

Most implemented papers

PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition

Gim Hee Lee, M. Uy•Mon Apr 09 2018

This paper proposes a combination/modification of the existing PointNet and NetVLAD, which allows end-to-end training and inference to extract the global descriptor from a given 3D point cloud, and proposes the "lazy triplet and quadruplet" loss functions that can achieve more discriminative and generalizable global descriptors to tackle the retrieval task.

648

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

RobotCar Seasons v2

RobotCar Seasons v2

Extended CMU Seasons

Extended CMU Seasons

Aachen Day-Night v1.1 Benchmark

Aachen Day-Night v1.1 Benchmark

marialeyvallina/generalized_contras…

2 papers 84

mchancan/citylearn

2 papers 30

82magnolia/panoramic-localization

2 papers 19

DublinCity

DublinCity

DeepLoc

Long-term visual localization

Long-term visual localization

PhotoSynth

SeasonDepth

0

LoFTR: Detector-Free Local Feature Matching with Transformers

H. Bao, Xiaowei Zhou, Jiaming Sun, Zehong Shen, Yuang Wang•Wed Mar 31 2021

The proposed method, LoFTR, uses self and cross attention layers in Transformer to obtain feature descriptors that are conditioned on both images, and enables the method to produce dense matches in low-texture areas, where feature detectors usually struggle to produce repeatable interest points.

1640 0

Deep Closest Point: Learning Representations for Point Cloud Registration

Yue Wang, J. Solomon•Tue May 07 2019

This work proposes a learning-based method, titled Deep Closest Point (DCP), inspired by recent techniques in computer vision and natural language processing, that provides a state-of-the-art registration technique and evaluates the suitability of the learned features transferred to unseen objects.

955 0

Neighbourhood Consensus Networks

T. Pajdla, Josef Sivic, Mircea Cimpoi, A. Torii, Relja Arandjelović, Ignacio Rocco•Tue Oct 23 2018

An end-to-end trainable convolutional neural network architecture that identifies sets of spatially consistent matches by analyzing neighbourhood consensus patterns in the 4D space of all possible correspondences between a pair of images without the need for a global geometric model is developed.

430 0

Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses

Eric Brachmann, C. Rother•Thu May 09 2019

This work uses prior information to improve model hypothesis search, increasing the chance of finding outlier-free minimal sets and combines neural guidance with differentiable RANSAC to build neural networks which focus on certain parts of the input data and make the output predictions as good as possible.

270 0

Visual localization under appearance change: filtering approaches

Thanh-Toan Do, I. Reid, Tat-Jun Chin, Anh-Dzung Doan, Y. Latif, Yu Liu, Shin-Fang Ch'ng•Wed Sep 16 2020

It is shown that exploiting temporal continuity in the testing sequence significantly improves visual localization and achieves better results than state of the art approaches for the task on visual localization under significant appearance change.

7 0

University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization

Yunchao Wei, Zhedong Zheng, Yi Yang•Wed Feb 26 2020

It is argued that drones could serve as the third platform to deal with the geo-localization problem and propose a strong CNN baseline on this challenging dataset, named University-1652, which is the first drone-based geo- localization dataset and enables two new tasks, i.e., drone-view target localization and drone navigation.

344 0

From Coarse to Fine: Robust Hierarchical Localization at Large Scale

R. Siegwart, Paul-Edouard Sarlin, César Cadena, Marcin Dymczyk•Sat Dec 08 2018

HF-Net is proposed, a hierarchical localization approach based on a monolithic CNN that simultaneously predicts local features and global descriptors for accurate 6-DoF localization and sets a new state-of-the-art on two challenging benchmarks for large-scale localization.

1065 0

BARF: Bundle-Adjusting Neural Radiance Fields

A. Torralba, S. Lucey, Wei-Chiu Ma, Chen-Hsuan Lin•Mon Apr 12 2021

Bundle-Adjusting Neural Radiance Fields (BARF) is proposed for training NeRF from imperfect (or even unknown) camera poses — the joint problem of learning neural 3D representations and registering camera frames and it is shown that coarse-to-fine registration is also applicable to NeRF.

830 0

Adding a benchmark result helps the community track progress.

Visual Localization | State-of-the-Art