Image-Based Localization
21 papers with code • 4 benchmarks • 6 datasets
Determining the location of an image without GPS based on cross-view matching. In most of the cases a database of satellite images is used to match the ground images to them.
Benchmarks
These leaderboards are used to track progress in Image-Based Localization
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
Datasets
CVUSA
NAVER LABS Localization Datasets
Most implemented papers
Stochastic Attraction-Repulsion Embedding for Large Scale Image Localization
This paper tackles the problem of large-scale image-based localization (IBL) where the spatial location of a query image is determined by finding out the most similar reference images in a large database.
University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization
layumi/University1652-Baseline
•
•
To our knowledge, University-1652 is the first drone-based geo-localization dataset and enables two new tasks, i. e., drone-view target localization and drone navigation.
SPP-Net: Deep Absolute Pose Regression with Synthetic Views
In this work we design a deep neural network architecture based on sparse feature descriptors to estimate the absolute pose of an image.
Optimal Feature Transport for Cross-View Image Geo-Localization
shiyujiao/cross_view_localization_CVFT
•
•
This paper proposes a novel Cross-View Feature Transport (CVFT) technique to explicitly establish cross-view domain transfer that facilitates feature alignment between ground and aerial images.
Cascaded Parallel Filtering for Memory-Efficient Image-Based Localization
Image-based localization (IBL) aims to estimate the 6DOF camera pose for a given query image.
Spatial-Aware Feature Aggregation for Image based Cross-View Geo-Localization
shiyujiao/SAFA
•
•
NeurIPS 2019
The first step is to apply a regular polar transform to warp an aerial image such that its domain is closer to that of a ground-view panorama.
Each Part Matters: Local Patterns Facilitate Cross-view Geo-localization
wtyhub/LPN
•
•
Existing methods usually concentrate on mining the fine-grained feature of the geographic target in the image center, but underestimate the contextual information in neighbor areas.
Domain-invariant Similarity Activation Map Contrastive Learning for Retrieval-based Long-term Visual Localization
HanjiangHu/DISAM
•
•
Visual localization is a crucial component in the application of mobile robot and autonomous driving.
DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based Localization
Long-Term visual localization under changing environments is a challenging problem in autonomous driving and mobile robotics due to season, illumination variance, etc.
P1AC: Revisiting Absolute Pose From a Single Affine Correspondence
We introduce the first general solution to the problem of estimating the pose of a calibrated camera given a single observation of an oriented point and an affine correspondence.
