Beast code in Giters

Shaohui Liu's repositories

TrianFlow

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

Language:PythonMIT264 10 30

DIST-Renderer

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

Language:PythonMIT215 11 7

NDiv

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

Language:Python10 3 1

colmap

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

Language:C++NOASSERTION4 20

JLinkage

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.

Language:C++GPL-2.03 20

Line3Dpp

Line3D++ - Multi-View Stereo using Line Segments

Language:C++MPL-2.01 10

MiDaS

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"

Language:JavaMIT100

PoseLib

Minimal solvers for calibrated camera pose estimation

Language:C++BSD-3-Clause1 10

blender

Official mirror of Blender

Language:CNOASSERTION010

ceres-solver

A large scale non-linear optimization library

Language:C++NOASSERTION010

cube_slam

CubeSLAM: Monocular 3D Object Detection and SLAM

Language:C++NOASSERTION020

DeepLSD

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

Language:Jupyter NotebookMIT000

DeepSDF

Learning Continuous Signed Distance Functions for Shape Representation

Language:PythonMIT010

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

Language:C++NOASSERTION000