Skip to content

Latest commit

 

History

History
215 lines (170 loc) · 27.2 KB

README.md

File metadata and controls

215 lines (170 loc) · 27.2 KB

Awesome Visual Localization

A curated list of visual (re)localization related resources, inspired by awesome-computer-vision. The list focuses on the research of visual localization, i.e. estimates 6 DoF camera poses of query RGB/RGB-D frames in known scenes (with databases).

This document is a work in progress. Please suggest papers/resources through pull requests. If you believe this list is missing something or has factually inaccurate info, you can also new an issue. All contributions are appreciated.

Table of Contents

Image Retrieval

  • [2023 ICCV] EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition [paper] [code]
  • [2022 CVPR] Rethinking Visual Geo-localization for Large-Scale Applications [paper] [code]
  • [2022 IJCV] Investigating the Role of Image Retrieval for Visual Localization - An exhaustive benchmark [paper]
  • [2020 ECCV] Self-supervising Fine-grained Region Similarities for Large-scale Image Localization [paper] [code]
  • [2020 3DV] Benchmarking Image Retrieval for Visual Localization [paper]
  • [2019 ICCV] Learning with Average Precision: Training Image Retrieval with a Listwise Loss [paper] [code]
  • [2018 CVPR] PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition [paper] [code]
  • [2017 CVPR] Large-Scale Image Retrieval with Attentive Deep Local Features [paper]
  • [2016 CVPR] NetVLAD: CNN architecture for weakly supervised place recognition [paper] [code]
  • [2016 CVPR] Large-Scale Location Recognition and the Geometric Burstiness Problem [paper] [code]
  • [2015 CVPR] 24/7 place recognition by view synthesis [paper] [code]
  • [2014 TVCG] Real-Time RGB-D Camera Relocalization via Randomized Ferns for Keyframe Encoding [paper]
  • [2013 CVPR] All about VLAD [paper]
  • [2012 BMVC] Image Retrieval for Image-Based Localization Revisited [paper]
  • [2012 BMVC] 6D Relocalisation for RGBD Cameras Using Synthetic View Regression
  • [2011 IROS] Real-Time Loop Detection with Bags of Binary Words [paper]

Camera Pose Regression

  • [2024 arXiv] Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization [paper] [code]
  • [2024 ECCV] Learning Neural Volumetric Pose Features for Camera Localization [paper]
  • [2024 CVPR] Map-Relative Pose Regression for Visual Re-Localization [paper] [code]
  • [2023 AAAI] RobustLoc: Robust Camera Pose Regression in Challenging Driving Environments [paper] [code]
  • [2022 ECCV] Map-Free Visual Relocalization: Metric Pose Relative to a Single Image [paper] [code]
  • [2022 ECCV] DFNet: Enhance Absolute Pose Regression with Direct Feature Matching [paper] [code]
  • [2022 ECCV] Camera Pose Auto-Encoders for Improving Pose Regression [paper] [code]
  • [2022 WACV] CoordiNet: uncertainty-aware pose regressor for reliable vehicle localization [paper]
  • [2021 3DV] Direct-PoseNet: Absolute Pose Regression with Photometric Consistency [paper] [code]
  • [2021 3DV] Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision [paper] [code]
  • [2021 ICCV] Learning Multi-Scene Absolute Pose Regression with Transformers [paper] [code]
  • [2021 ICRA] Learning to Localize in New Environments from Synthetic Training Data [paper] [code]
  • [2021 CoRL] LENS: Localization enhanced by NeRF synthesis [paper]
  • [2020 ECCV] 6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference [paper] [code]
  • [2020 CVPR] Learning Multi-view Camera Relocalization with Graph Neural Networks [paper]
  • [2020 AAAI] AtLoc: Attention Guided Camera Localization [paper] [code]
  • [2019 ECCV] CamNet: Coarse-to-Fine Retrieval for Camera Re-Localization [paper]
  • [2019 CVPR] Understanding the Limitations of CNN-based Absolute Camera Pose Regression [paper]
  • [2018 ECCV] RelocNet: Continuous Metric Learning Relocalisation using Neural Nets [paper]
  • [2018 BMVC] Improved Visual Relocalization by Discovering Anchor Points [paper] [code]
  • [2018 CVPR] Geometry-Aware Learning of Maps for Camera Localization [paper] [code]
  • [2018 RA-L] VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometry [paper]
  • [2017 ICCV Workshop] Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network [paper] [code]
  • [2017 IROS] Deep regression for monocular camera-based 6-dof global localization in outdoor environments [paper]
  • [2017 CVPR] Geometric loss functions for camera pose regression with deep learning [paper]
  • [2017 CVPR] Image-based localization using LSTMs for structured feature correlation [paper]
  • [2016 ICRA] Modelling Uncertainty in Deep Learning for Camera Relocalization [paper]
  • [2015 ICCV] PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization [paper]

Feature Matching

  • [2024 ECCV] Grounding Image Matching in 3D with MASt3R [paper] [code]
  • [2024 CVPR] RoMa: Robust Dense Feature Matching [paper] [code]
  • [2024 CVPR] Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed [paper] [code]
  • [2024 CVPR] Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences [paper] [code]
  • [2024 CVPR] DeViLoc: Learning to Produce Semi-dense Correspondences for Visual Localization [paper] [code]
  • [2024 CVPR] DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching [paper] [code]
  • [2023 ICCV] LightGlue: Local Feature Matching at Light Speed [paper] [code]
  • [2023 ICCV] Guiding Local Feature Matching with Surface Curvature [paper] [code]
  • [2022 ECCV] MeshLoc: Mesh-Based Visual Localization [paper] [code]
  • [2022 CVPR] SceneSqueezer: Learning to Compress Scene for Camera Relocalization [paper]
  • [2021 IJCV] Reference Pose Generation for Long-term Visual Localization via Learned Features and View Synthesis [paper]
  • [2021 ICCV Workshop] MegLoc: A Robust and Accurate Visual Localization Pipeline [paper]
  • [2021 ICCV Workshop] Pose Refinement with Joint Optimization of Visual Points and Lines [paper]
  • [2021 ICRA & ICCV Workshop] Retrieval and Localization with Observation Constraints [paper]
  • [2021 CVPR] Back to the Feature: Learning Robust Camera Localization from Pixels to Pose [paper] [code]
  • [2021 CVPR] LoFTR: Detector-Free Local Feature Matching with Transformers [paper] [code]
  • [2020 3DV] Using Image Sequences for Long-Term Visual Localization [paper]
  • [2020 ECCV Workshop] Hierarchical Localization with hloc and SuperGlue [slides] [code]
  • [2020 IROS] KR-Net: A Dependable Visual Kidnap Recovery Network for Indoor Spaces [paper]
  • [2020 ICRA] To Learn or Not to Learn: Visual Localization from Essential Matrices [paper]
  • [2020 arXiv] Robust Image Retrieval-based Visual Localization using Kapture [paper] [code]
  • [2019 CVPR] From Coarse to Fine: Robust Hierarchical Localization at Large Scale [paper] [code]
  • [2019 CVPR] D2-Net: A Trainable CNN for Joint Description and Detection of Local Features [paper] [code]
  • [2018 CoRL] Leveraging Deep Visual Descriptors for Hierarchical Efficient Localization [paper] [code]
  • [2018 CVPR] InLoc: Indoor Visual Localization with Dense Matching and View Synthesis [paper] [code]
  • [2017 ICCV] Efficient Global 2D-3D Matching for Camera Localization in a Large-Scale 3D Map [paper]
  • [2017 CVPR] Are Large-Scale 3D Models Really Necessary for Accurate Visual Localization? [paper]
  • [2017 ICRA] [RA-L] Self-supervised Visual Descriptor Learning for Dense Correspondence [paper]
  • [2016 TPAMI] Efficient & Effective Prioritized Matching for Large-Scale Image-Based Localization [paper]
  • [2015 ICCV] Camera Pose Voting for Large-Scale Image-Based Localization [paper]
  • [2012 ECCV] Improving Image-Based Localization by Active Correspondence Search [paper] [code]
  • [2012 CVPR] Real-time Image-based 6-DOF Localization in Large-Scale Environments [paper]
  • [2011 ICCV] Fast Image-Based Localization using Direct 2D-to-3D Matching [paper]

Scene Coordinate Regression

  • [2025 arXiv] R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization [paper] [code]
  • [2024 ECCV] Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer [paper] [code]
  • [2024 CVPR] DUSt3R: Geometric 3D Vision Made Easy [paper] [code]
  • [2024 CVPR] GLACE: Global Local Accelerated Coordinate Encoding [paper] [code]
  • [2024 CVPR Workshop] SACReg: Scene-Agnostic Coordinate Regression for Visual Localization [paper]
  • [2024 IJCV] HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer [paper]
  • [2023 CVPR] Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses [paper] [code]
  • [2022 3DV] Visual Localization via Few-Shot Scene Region Classification [paper] [code]
  • [2022 ECCV] Towards Accurate Active Camera Localization [paper] [code]
  • [2022 CVPR] CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data [paper] [code]
  • [2021 ICCV] Continual Learning for Image-Based Camera Localization [paper] [code]
  • [2021 TPAMI] Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC [paper] [code]
  • [2021 CVPR] Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments [paper] [code]
  • [2021 CVPR] Learning Camera Localization via Dense Scene Matching [paper] [code]
  • [2021 CVPR] VS-Net: Voting with Segmentation for Visual Localization [paper] [code]
  • [2020 CVPR] KFNet: Learning Temporal Camera Relocalization using Kalman Filtering [paper] [code]
  • [2020 CVPR] Hierarchical Scene Coordinate Classification and Regression for Visual Localization [paper] [code]
  • [2019 3DV] Let’s Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation [paper]
  • [2019 TPAMI] Real-Time RGB-D Camera Pose Estimation in Novel Scenes using a Relocalisation Cascade [paper] [code]
  • [2019 ICCV] SANet: Scene Agnostic Network for Camera Localization [paper] [code]
  • [2019 ICCV] Expert Sample Consensus Applied to Camera Re-Localization [paper] [code]
  • [2018 IROS] Exploiting Points and Lines in Regression Forests for RGB-D Camera Relocalization [paper]
  • [2018 RSS] Full-Frame Scene Coordinate Regression for Image-Based Localization [paper]
  • [2018 CVPR] Learning Less is More – 6D Camera Localization via 3D Surface Regression [paper] [code]
  • [2017 IROS] Backtracking Regression Forests for Accurate Camera Relocalization [paper]
  • [2017 CVPR] DSAC - Differentiable RANSAC for Camera Localization [paper] [code]
  • [2017 CVPR] On-the-Fly Adaptation of Regression Forests for Online Camera Relocalisation [paper] [code]
  • [2017 ICRA] Random Forests versus Neural Networks − What’s Best for Camera Localization? [paper]
  • [2016 CVPR] Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image [paper]
  • [2015 CVPR] Exploiting Uncertainty in Regression Forests for Accurate Camera Relocalization [paper]
  • [2014 CVPR] Multi-Output Learning for Camera Relocalization [paper]
  • [2013 CVPR] Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images [paper]

Camera Pose Optimization and Refinement

  • [2024 arXiv] GSLoc: Efficient Camera Pose Refinement via 3D Gaussian Splatting [paper]
  • [2024 ECCV] Robust Incremental Structure-from-Motion with Hybrid Features [paper]
  • [2024 ECCV] Global Structure-from-Motion Revisited [paper] [code]
  • [2024 ECCV] Gravity-aligned Rotation Averaging with Circular Regression [paper] [code]
  • [2024 ECCV] StereoGlue: Robust Estimation with Single-Point Solvers [paper] [code]
  • [2024 CVPR] Absolute Pose from One or Two Scaled and Oriented Features [paper] [code]
  • [2024 CVPR] Neural Refinement for Absolute Pose Regression with Feature Synthesis [paper] [code]
  • [2024 ICRA] HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisation [paper] [code]
  • [2024 3DV] Self-Supervised Learning of Neural Implicit Feature Fields for Camera Pose Refinement [paper]
  • [2023 arXiv] Lazy Visual Localization via Motion Averaging [paper]
  • PoseLib
  • RansacLib
  • [2016 CVPR] Structure-from-Motion Revisited [paper] [code]

Datasets and Benchmarks

In/Outdoor

Indoor

Outdoor

Challenges

Tools