Official repository for the ICLR 2024 paper "Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition".

BoQ: A Place is Worth a Bag of learnable Queries (CVPR 2024)

Official repository for the CVPR 2024 paper "CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition".

Official repository for the AAAI 2024 paper "Deep Homography Estimation for Visual Place Recognition".

Official repository for the NeurIPS 2024 paper "SuperVLAD: Compact and Robust Image Descriptors for Visual Place Recognition".

Official repository for the NeurIPS 2025 paper "Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era".

Official repository for the T-PAMI 2025 paper "SelaVPR++: Towards Seamless Adaptation of Foundation Models for Efficient Place Recognition".

This repository is containing an object classification & localization project for SINGLE object.

EFGHNet: A Versatile Image-to-Point Cloud Registration Network for Extreme Outdoor Environment

Matches image sequences given a similarity matrix

dnn-locate is a python module for discriminative features localization based on neural networks.

Implementation of the paper "Style Transfer for Keypoint Matching under Adverse Condition"

EndoCheck is a web application that allows doctors to automatically process endoscopic images or videos of patients to screen for anomalies.

Codex skill for localizing ad creatives into multilingual, platform-ready image assets.

Automatic localization of optic disc and fovea using only image processing techniques.

Local-first manga OCR, coherent translation, and artwork-preserving text replacement.

STM32 Controller+Image Localization NYCU

A system of vector search and exact feature matching built for fast location pinpointing in a city.

Quality-first Chinese-to-Thai image localization with self-hosted Gemma 4 12B, OCR, deterministic rendering, and hard QA.

Pluggable end-to-end image localization framework: OCR, translation, text inpainting, rendering and automated quality checks in one pipeline, delivering localized manga, illustrations, game UI and documents with local-first fully-offline operation.