[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.

湖南大学硕士学位论文Latex模版

Code release for ConvNeXt V2 model

GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)

a simple test convert roma image matche model to tensorrt

Code of single-view depth prediction algorithm on Internet Photos described in "MegaDepth: Learning Single-View Depth Prediction from Internet Photos, Z. Li and N. Snavely, CVPR 2018".

[CVPR 2025] MINIMA: Modality Invariant Image Matching

😼 优雅地使用基于 clash/mihomo 的代理环境

MapGlue: Multimodal Remote Sensing Image Matching

[CVPR 2025] JamMa is a lightweight image matcher that enables fast internal and mutual interaction of images with joint Mamba.

Equivariant Steerable CNNs Library for Pytorch https://quva-lab.github.io/escnn/

Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!

Code for "Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed", CVPR 2024

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

[AAAI 2025 Oral🚁] Game4Loc: A UAV Geo-Localization Benchmark from Game Data

[🎉IEEE TGRS'24] The official code for paper "CAMP: A Cross-View Geo-Localization Method using Contrastive Attributes Mining and Position-aware Partitioning"

「TIP2023」Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments

[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.

UAV Visual Localization

Linux环境安装配置Clash工具，以实现代理上网效果。包含下载、安装、配置、运行、测试以及开机自启动、定期自动更新订阅功能的操作文档，希望对你有所帮助

基于Clash Core 制作的Clash For Linux备份仓库 A Clash For Linux Backup Warehouse Based on Clash Core

ONNX-TensorRT: TensorRT backend for ONNX

这个仓库用来整理研究时用过的一些数据集

[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

A lightweight and real-time DETR for aerial images detection