Sceneform SDK for Android

Locality Preserving Matching

Models and examples built with TensorFlow

20x Real-time superpixel SLIC Implementation with CPU

The convertor/conversion of deep learning models for different deep learning frameworks/softwares.

A high-quality ellipse detector based on arc-support line segments which can both accurately and efficiently detect ellipses in images.

DeMoN: Depth and Motion Network

A complete tutorial to reproduce Fast Depth Densification for Occlusion-aware Augmented Reality (SIGGRAPH-Asia 2018), as well as a script to show effects on custom videos.

An implementation of stixel computation

A CUDA implementation of Segmentation SGM

Distance Estimation using Monocular Camera system

Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO demo to detect raccoon run entirely in brower is accessible at https://git.io/vF7vI (not on Windows).

Create paths for your Augmented Reality environments using just points to represent the centre of the path.

C++ code for QuEst: a quaternion-based approach for camera motion estimation from minimal feature points (https://ieeexplore.ieee.org/document/8253803)

NanoPM, single header only PatchMatch

Disparity and depth maps GUI with QT and OpenCV with support for classic image files and MPO stereo pairs

A tutorial on stereoscopic depth maps, focusing on triangulation and rectification

Dense disparity estimation via local stereo matching

The challenge projects for Inferencing machine learning models on iOS

A real-time depth filling approach based on prior image segmentation

papers and code for depth completion

Official pytorch implementation of "Indoor Depth Completion with Boundary Consistency and Self-Attention. Huang et al. RLQ@ICCV 2019."

Stixel c++ code based on gish523's algo.

Stereo Semi Global Matching by cuda

ICRA 2019 "FastDepth: Fast Monocular Depth Estimation on Embedded Systems"

Implementation of the Instance Stixel pipeline. Paper:

📝 A curated list of image rectification papers.

Deeper Depth Prediction with Fully Convolutional Residual Networks (FCRN)