awesome-visual-localization-papers
The relocalization task aims to estimate the 6-DoF pose of a novel (unseen) frame in the coordinate system given by the prior model of the world.
https://github.com/Dylancer1998/awesome-visual-localization-papers
Last synced: 5 days ago
JSON representation
-
Uncategorized
-
Uncategorized
- KFNet: Learning Temporal Camera Relocalization using Kalman Filtering
- Robust Neural Routing Through Space Partitions for Camera Relocalizationin Dynamic Indoor Environments
- R2D2: Repeatable and Reliable Detector and Descriptor
- ASLFeat: Learning Local Features of Accurate Shape and Localization
- DISK: learning local features with policy gradient - epfl/disk)
- FisheyeSuperPoint: Keypoint Detection andDescription Network for Fisheye Images
- ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction
- Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints - yyjau/pytorch-deepFEPE)
- LoFTR: Detector-Free Local Feature Matching with Transformers
- MatchFormer: Interleaving Attention in Transformersfor Feature Matching
- City-Scale Localization for Cameras with Known Vertical Direction
- GC-RANSAC: Graph-Cut RANSAC - aiki/pydegensac)
- Learning Bipartite Graph Matching for Robust Visual Localization
- Multi-View Optimization of Local Feature Geometry - feature-refinement)
- Hybrid Rotation Averaging: A Fast and Robust Rotation Averaging Approach
- Is there anything new to say about SIFT matching?
- Cross-Descriptor Visual Localization and Mapping - descriptor-vis-loc-map
- ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer
- NetVLAD: CNN Architecture for Weakly Supervised Place Recognition
- Real-time self-localization from panoramic images on mobile devices
- DFM: A Performance Baseline for Deep Feature Matching
- Back to the Feature: Learning Robust Camera Localization from Pixels to Pose
- Camera Pose Voting for Large-Scale Image-Based Localization
- DSAC - Differentiable RANSAC for Camera Localization
- MAGSAC: marginalizing sample consensus
- Monocular RGB Scene Reconstruction using Transformers
- A Vote-and-Verify Strategy for Fast Spatial Verification in Image Retrieval - content/uploads/sites/6231/2016/06/schoenberger2016vote.pdf)
- City-Scale Localization for Cameras with Known Vertical Direction
- PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization
- Semantic Visual Localization
- Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task - Feature-Points)
- PoSFeat: Decoupling Makes Weakly Supervised Local Feature Better - Learning-And-Vision-Atelier-LAVA/PoSFeat)
- Gomsf: Graph-optimization based multi-sensor fusion for robust uav pose estimation
- PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization
- Image-based camera localization: an overview
- Wide area localization on mobile phones
- Parallel Tracking and Mapping on a Camera Phone
- Scalable 6-DOF Localization on Mobile Devices
- Image Matching Across Wide Baselines: From Paper to Practice - vision/image-matching-benchmark)
- Using Image Sequences for Long-Term Visual Localization
- Efficient 2D-3D Matching for Multi-Camera Visual Localization
- Intermittent GPS-aided VIO: Online Initialization and Calibration
- Fisher Kernels on Visual Vocabularies for Image Categorization
- Aggregating Local Descriptors Into a Compact Image Representation
- Fast image-based localization using direct 2D to-3D matching - aachen.de/software/image-localization/)
- Crossdimensional Weighting for Aggregated Deep Convolutional Features
- Efficient diffusion on region manifolds: Recovering small objects with compact cnn representations
- Revisiting Oxford and Paris: Large-scale Image Retrieval Benchmarking
- DPSNet: End-to-end Deep Plane Sweep Stereo
- 6D dynamic camera relocalization from single reference image
- GN-Net: The Gauss-Newton Loss for Multi-Weather Relocaliza-tion - ai/GN-Net-Benchmark)
- Robust Neural Routing Through Space Partitions for Camera Relocalizationin Dynamic Indoor Environments
- ASLFeat: Learning Local Features of Accurate Shape and Localization
- DISK: learning local features with policy gradient - epfl/disk)
- ACNe: Attentive Context Normalization for Robust Permutation Equivariant Learning - uvic/acne)
- Deep Kernelized Dense Geometric Matching
- Total Recall: Automatic Query Expansion with a Generative Feature Model for Object Retrieval
- Multi-sensor navigation algorithm using monocular camera, imu and gps for large scale augmented reality
- Vins Fusion — A General Optimization-based Framework for Global Pose Estimation with Multiple Sensors
- Consistent Video Depth Estimation
- KFNet: Learning Temporal Camera Relocalization using Kalman Filtering
- R2D2: Repeatable and Reliable Detector and Descriptor
- Learning Feature Descriptors using Camera Pose Supervision
- FisheyeSuperPoint: Keypoint Detection andDescription Network for Fisheye Images
- ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction
- Learning to Find Good Correspondences - uvic/learned-correspondence-release)
- OANet: Learning Two-View Correspondences and Geometry Using Order-Aware Network
- Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints - yyjau/pytorch-deepFEPE)
- SuperGlue: Learning Feature Matching with Graph Neural Networks
- LoFTR: Detector-Free Local Feature Matching with Transformers
- COTR: Correspondence Transformer for Matching Across Images - vision/COTR)
- Patch2Pix for Accurate Image Correspondence Estimation
- MatchFormer: Interleaving Attention in Transformersfor Feature Matching
- Learning with Average Precision: Training Image Retrieval with a Listwise Loss
- Benchmarking Image Retrieval for Visual Localization - localization">**[code]**</a>
- Fixing the Locally Optimized RANSAC
- GC-RANSAC: Graph-Cut RANSAC - aiki/pydegensac)
- DegenSac
- DARNavi: An Indoor-Outdoor Immersive Navigation System with Augmented Reality
- Neural Topological SLAM for Visual Navigation
- DeepSFM: Structure From Motion Via Deep Bundle Adjustment
- Multi-View Optimization of Local Feature Geometry - feature-refinement)
- Deepv2d: Video to depth with differentiable structure from motion
- Hybrid Rotation Averaging: A Fast and Robust Rotation Averaging Approach
- Pixel-Perfect Structure-from-Motion with Featuremetric Refinement - perfect-sfm)
- Visual Categorization with Bags of Keypoints
- Improving image-based localization by active correspondence search
- Aggregating Deep Convolutional Features for Image Retrieval
- Towards SLAM-based Outdoor Localization using Poor GPS and 2.5D Building Models
- TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo - vision/tandem)
- LM-Reloc: Levenberg-Marquardt Based Direct Visual Relocalization
- CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data - EPFL/CrossLoc) [**[dataset]**](https://doi.org/10.5061/dryad.mgqnk991c) [**[video]**](https://youtu.be/pytRRXPFqFE) [**[website]**](https://crossloc.github.io/)
- Fine-Tuning CNN Image Retrieval with no Human Annotation
- AdaLAM: Revisiting Handcrafted Outlier Detection
- Learning Bipartite Graph Matching for Robust Visual Localization
- Learnable Motion Coherence for Correspondence Pruning - pal/LMCNet)
- CLNet: Progressive Correspondence Pruning by Consensus Learning - z/CLNet)
-