Framework for aerial imagery localization using different VPR systems

pytorch memory track code

Explainability for Vision Transformers

assistant tools for attention visualization in deep learning

Code for "Detector-Free Structure from Motion", CVPR 2024

Pytorch implementation of convolutional neural network visualization techniques

Datasets for deep learning with satellite & aerial imagery

UAV-VisLoc: A Large-scale Dataset for UAV Visual Localization

NetVLAD: CNN architecture for weakly supervised place recognition

GNSS-Free drone navigation and localization in the wild

Automatic download VPR datasets in a standard format

Provide mapping and localization pipelines based on kapture format

This repository contains the codebase and all the relevant information for our IJCV paper on VPR-Bench: An open-source Visual Place Recognition Evaluation Framework

OpenSeqSLAM2 is a MATLAB toolbox for interactively exploring the visual place recognition problem.

kapture is a file format as well as a set of tools for manipulating datasets, and in particular Visual Localization and Structure from Motion data.

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

A personal list of papers and resources of image matching and pose estimation, including perspective images and panoramas.

[CVPR 2024 Highlight] Map-Relative Pose Regression for Visual Re-Localization

[CVPR 2022 Oral, Best Student Paper] EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

[CVPR 2024] Probing the 3D Awareness of Visual Foundation Models

[CVPR 2024🔥] Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization

H2RSVLM: Towards Helpful and Honest Remote Sensing Large Vision Language Model

Official code of Remote Sensing Mamba

Attention \ Saliency maps and features visualization for deep learning models in pytorch

同济子豪兄的公开课