A collection of infrastructure and tools for research in neural network interpretability.

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

Code for "PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation" CVPR 2019 oral

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

Joint deep network for feature line detection and description

Code release for "learning to find good correspondences" CVPR 2018

Deep Declarative Networks

A Smooth Representation of SO(3) for Deep Rotation Learning with Uncertainty.

Real-time robotic object pose estimation with deep learning

Official PyTorch implementation of GoMatch -- "Is Geometry Enough for Matching in Visual Localization" [ECCV2022]

Python interface for SCS