https://threejs.org/editor/, JavaScript 3D Library.

Adapted COLMAP intended to work with satellite images

Out-of-Core Surface Reconstruction via Global TGV Minimization, Nikolai Poliarnyi, ICCV 2021

Code for the CVPR2021 paper "Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition"

Visual localization made easy with hloc

PopSift is an implementation of the SIFT algorithm in CUDA.

photo panorama converter

Fast reconstruction of spatial networks from bioimages.

open Multi-View Stereo reconstruction library

[ECCV 2020] Single image depth prediction allows us to rectify planar surfaces in images and extract view-invariant local features for better feature matching

Deep image retrieval for efficient 6-DoF localization

Implementation of Vector of Locally Aggregated Descriptors (VLAD)

Pytorch implementation of NetVlad including training on Pittsburgh.

SGM implementation

Compute Vanishing points using RANSAC and rectify the image

A numpy implementation of "planar filtering" of "Depth from motion for smartphone AR", Valentin et al., SIGGRAPH Asia 2018

A CUDA implementation of SIFT for NVidia GPUs (1.2 ms on a GTX 1060)

Efficient neural feature detector and descriptor

Fuse multiple depth frames into a point cloud

Stereo Semi Global Matching by cuda

Algorithm to texture 3D reconstructions from multi-view stereo images

Stereo and image rectification and disparity processing with NVIDIA VisionWorks and fixstars libSGM

GA-Net: Guided Aggregation Net for End-to-end Stereo Matching

Efficient Coarse-to-Fine PatchMatch for Large Displacement Optical Flow, CVPR 2016

Fast Bilateral Solver implementation with C++ and demos

C++ implementation of Fast Depth Densification for Occlusion-aware Augmented Reality (SIGGRAPH-Asia 2018)