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-10

Camera Relocalization

3260 papers • 126 benchmarks • 313 datasets

"Camera relocalization, or image-based localization is a fundamental problem in robotics and computer vision. It refers to the process of determining camera pose from the visual scene representation and it is essential for many applications such as navigation of autonomous vehicles, structure from motion (SfM), augmented reality (AR) and simultaneous localization and mapping (SLAM)." (Source)

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in camera-relocalization-10

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find camera-relocalization-10 models and implementations

Datasets

Cambridge Landmarks

Cambridge Landmarks

DeepLoc

Subtasks

camera absolute pose regression

Most implemented papers

6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference

Shadi Albarqouni, L. Guibas, N. Navab, Slobodan Ilic, Tolga Birdal, Haowen Deng, Mai Bui•Wed Apr 08 2020

A multimodal camera relocalization framework that captures ambiguities and uncertainties with continuous mixture models defined on the manifold of camera poses, using Bingham distributions and a multivariate Gaussian to model the position, with an end-to-end deep neural network.

31

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

Modelling uncertainty in deep learning for camera relocalization

Alex Kendall, R. Cipolla•Fri Sep 18 2015

A Bayesian convolutional neural network is used to regress the 6-DOF camera pose from a single RGB image and an estimate of the model's relocalization uncertainty is obtained to improve state of the art localization accuracy on a large scale outdoor dataset.

577 0

Backtracking regression forests for accurate camera relocalization

J. Little, Julien P. C. Valentin, Jianhui Chen, Lili Meng, Frederick Tung, C. D. Silva•Thu Aug 31 2017

A sample-balanced objective to encourage equal numbers of samples in the left and right sub-trees, and a novel backtracking scheme to remedy the incorrect 2D-3D correspondence predictions are proposed.

61 0

VMLoc: Variational Fusion For Learning-Based Multimodal Camera Localization

A. Markham, Kaichen Zhou, Changhao Chen, Bing Wang, Muhamad Risqi U. Saputra, Niki Trigoni•Wed Mar 11 2020

This work proposes an end-to-end framework, termed VMLoc, to fuse different sensor inputs into a common latent space through a variational Product-of-Experts (PoE) followed by attention-based fusion, and shows how camera localization can be accurately estimated through an unbiased objective function based on importance weighting.

25 0

KFNet: Learning Temporal Camera Relocalization Using Kalman Filtering

Yao Yao, Zixin Luo, Lei Zhou, Tian Fang, Long Quan, Tianwei Shen, Jiahui Zhang, Mingmin Zhen•Mon Mar 23 2020

KFNet extends the scene coordinate regression problem to the time domain in order to recursively establish 2D and 3D correspondences for the pose determination in temporal relocalization using a network architecture based on Kalman filtering in the context of Bayesian learning.

86 0

Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes

S. Golodetz, Federico Tombari, Johanna Wald, Torsten Sattler, Tommaso Cavallari•Tue Aug 04 2020

This paper adapts 3RScan - a recently introduced indoor RGB-D dataset designed for object instance re-localization - to create RIO10, a new long-term camera re- localization benchmark focused on indoor scenes and explores how state-of-the-art cameraRe-localizers perform according to these metrics.

54 0

Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments

L. Guibas, T. Funkhouser, He Wang, Li Yi, Baoquan Chen, Siyan Dong, Qingnan Fan, Ji Shi•Mon Dec 07 2020

This paper proposes a novel outlier-aware neural tree which bridges the two worlds, deep learning and decision tree approaches and outperforms the state-of-the-art approaches by around 30% on camera pose accuracy, while running comparably fast for evaluation.

29 0

Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimation

L. Guibas, N. Navab, Slobodan Ilic, Tolga Birdal, Haowen Deng, Mai Bui•Sat Dec 19 2020

This work introduces Deep Bingham Networks (DBN), a generic framework that can naturally handle pose-related uncertainties and ambiguities arising in almost all real life applications concerning 3D data, and proposed new training strategies so as to avoid mode or posterior collapse during training and to improve numerical stability.

65 0

Direct-PoseNet: Absolute Pose Regression with Photometric Consistency

V. Prisacariu, Zirui Wang, Shuai Chen•Wed Apr 07 2021

This work designs a direct matching module that supplies a photometric supervision signal to refine the pose regression network via differentiable rendering and shows that the method can easily cope with additional unlabeled data without the need for external supervision.

79 0

Adding a benchmark result helps the community track progress.

Camera Relocalization | State-of-the-Art