Learned Perceptual Image Patch Similarity (LPIPS) metric. In CVPR, 2018.
Performs Locality-Sensitive Hashing on images after computing their feature vectors using a feature detection algorithm like BRIEF or SIFT. Stores the result in an LSHash object using Redis. When querying a new image, a feature detection algorithm is run on it and after performing a similarity search, the closest matching image from the dataset is returned.
Open source Python module for computer vision based on which I make some adaptations for Python 3
A simple monocular visual odometry (part of vSLAM) with initialization, tracking, local map and bundle adjustment. (Hi, this project is not good enough to be used in real scene)
Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities
Code for GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose (CVPR 2018)
PyTorch implementation of the CVPR 2018 (oral) paper "MapNet: An Allocentric Spatial Memory for Mapping Environments" (Henriques and Vedaldi)
Python demo to our CVPR'19 publication: Mapping, Localization and Path Planning for Image-based Navigation using Visual Features and Map
Collection of papers and other resources for object tracking and detection using deep learning
