Mihai Dusmanu

d2-net. D2-Net: A Trainable CNN for Joint Description and Detection of Local Features

local-feature-refinement. Multi-View Optimization of Local Feature Geometry

cross-descriptor-vis-loc-map. Cross-Descriptor Visual Localization and Mapping

torch-feature-matching. Different feature matching algorithms implemented in PyTorch!

privacy-preserving-image-features. Privacy-Preserving Image Features via Adversarial Affine Subspace Embeddings

local-feature-evaluation-vis. Visualisation tools for "Comparative Evaluation of Hand-Crafted and Learned Local Features"

netvlad. NetVLAD: CNN architecture for weakly supervised place recognition

SuperPointPretrainedNetwork. PyTorch pre-trained model for real-time interest point detection, description, and sparse tracking (https://arxiv.org/abs/1712.07629)

pytorch-sann. Spatially Aware Nearest Neighbors for PyTorch

Hierarchical-Localization. Visual localization made easy with hloc

image-matching-benchmark-baselines. Baselines for the Image Matching Benchmark and Challenge

large-scale-ssl. Large Graph Construction for Scalable Semi-Supervised Learning

serve. Serve, optimize and scale PyTorch models in production

image-matching-benchmark. Public release of the Image Matching Benchmark: https://image-matching-challenge.github.io

SmilkNel-rest-tutorial. Shell

SuperGluePretrainedNetwork. SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

KPNs. Kahn process networks.

local-feature-evaluation. Comparative Evaluation of Hand-Crafted and Learned Local Features