Shaohui Liu

ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild. ECCV 2022.

COLMAP - Structure-from-Motion and Multi-View Stereo

DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracing (CVPR 2020).

Code release for "Towards Better Generalization: Joint Depth-Pose Learning without PoseNet".

Class-Aware Frechet Distance (CAFD) for GANs in Tensorflow. Source code for "An Improved Evaluation Framework for Generative Adversarial Networks".

Implementation of "Normalized Diversification (NDiv)" in Pytorch and Tensorflow.

JLinkage is the most popular method for detecting vanishing point and this repository is the C++ version of JLinkage which can be directly used in Linux.

Minimal solvers for calibrated camera pose estimation

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

Line3D++ - Multi-View Stereo using Line Segments

The fastest repo in history to surpass 50K stars ⭐, reaching the milestone in just 2 hours after publication. Better Harness Tools that make real things done. Now writing in Rust using oh-my-codex.

No description.

Fast symbolic computation, code generation, and nonlinear optimization for robotics

Depth Anything 3

Factor graphs with Ceres in Python

Visual localization made easy with hloc

Joint Deep Matcher for Points and Lines 🖼️💥🖼️ (ICCV 2023)

Python transparent bindings for LSD (Line Segment Detector)

Source code for the ECCV 2022 paper "Benchmarking Localization and Mapping for Augmented Reality".

Implementation of the paper "DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients"

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

Template-based implementation of RANSAC and its variants in C++

The ultimate Vim configuration (vimrc)

An open source library for multiview geometry and structure from motion

No description.

The Graph-Cut RANSAC algorithm proposed in paper: Daniel Barath and Jiri Matas; Graph-Cut RANSAC, Conference on Computer Vision and Pattern Recognition, 2018. It is available at http://openaccess.thecvf.com/content_cvpr_2018/papers/Barath_Graph-Cut_RANSAC_CVPR_2018_paper.pdf

Official mirror of Blender

Joint deep network for feature line detection and description

Simple C++ geometry processing library.

Python bindings for COLMAP estimators

A large scale non-linear optimization library

HighFive - Header-only C++ HDF5 interface

No description.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

nanoflann: a C++11 header-only library for Nearest Neighbor (NN) search with KD-trees

Repository for OpenCV's extra modules

Learning Continuous Signed Distance Functions for Shape Representation

A Computer Graphics Library

CubeSLAM: Monocular 3D Object Detection and SLAM

OpenEXR is a high dynamic-range (HDR) image file format developed by Industrial Light & Magic for use in computer imaging applications

LiFF Light Field Feature Toolbox

Python library for loading and using triangular meshes.

A repository for updates to libhand (www.libhand.org)

OpenPose: Real-time multi-person keypoint detection library for body, face, and hands estimation

Convolutional Neural Networks

(CVPR'17) Training a Correlation Filter end-to-end allows lightweight networks of 2 layers (600 kB) to achieve state-of-the-art performance in tracking, at high-speed.

Source code for paper: Learning to Track at 100 FPS with Deep Regression Networks, Held, et al. ECCV 2016