TingmanYan / Sdr
Licence: gpl-3.0
Code for 'Segment-based Disparity Refinement with Occlusion Handling for Stereo Matching'
Stars: ✭ 80
Labels
Projects that are alternatives of or similar to Sdr
one-click-tangle
"One Click Tangle" intends to make lives easier to IOTA adopters by providing pre-configured scripts and recipes that allow to deploy IOTA Networks and Nodes "in one click".
Stars: ✭ 43 (-46.25%)
Mutual labels: depth
Mosdepth
fast BAM/CRAM depth calculation for WGS, exome, or targeted sequencing
Stars: ✭ 376 (+370%)
Mutual labels: depth
Astradotnetdemo
Simple .Net solution to demonstrate working with Orbbec Astra (Pro) depth sensors from C#
Stars: ✭ 28 (-65%)
Mutual labels: depth
depth-from-defocus-and-correspondence
⛄Depth from Combining Defocus and Correspondence Using Light-Field Cameras.
Stars: ✭ 17 (-78.75%)
Mutual labels: depth
Spherelayout
a layout which supports 3d rotate and enable its childview has z-depth for android
Stars: ✭ 55 (-31.25%)
Mutual labels: depth
Stereonet Activestereonet
stereo matching StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth prediction model in pytorch. ECCV2018; ActiveStereoNet:End-to-End Self-Supervised Learning for Active Stereo Systems ECCV2018 Oral
Stars: ✭ 308 (+285%)
Mutual labels: depth
learning-topology-synthetic-data
Tensorflow implementation of Learning Topology from Synthetic Data for Unsupervised Depth Completion (RAL 2021 & ICRA 2021)
Stars: ✭ 22 (-72.5%)
Mutual labels: depth
Revisiting single depth estimation
official implementation of "Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries"
Stars: ✭ 271 (+238.75%)
Mutual labels: depth
Depth clustering
🚕 Fast and robust clustering of point clouds generated with a Velodyne sensor.
Stars: ✭ 657 (+721.25%)
Mutual labels: depth
M4Depth
Official implementation of the network presented in the paper "M4Depth: A motion-based approach for monocular depth estimation on video sequences"
Stars: ✭ 62 (-22.5%)
Mutual labels: depth
Flutter Neumorphic
A complete, ready to use, Neumorphic ui kit for Flutter, 🕶️ dark mode compatible
Stars: ✭ 988 (+1135%)
Mutual labels: depth
G2LTex
Code for CVPR 2018 paper --- Texture Mapping for 3D Reconstruction with RGB-D Sensor
Stars: ✭ 104 (+30%)
Mutual labels: depth
Arcore Depth Lab
ARCore Depth Lab is a set of Depth API samples that provides assets using depth for advanced geometry-aware features in AR interaction and rendering. (UIST 2020)
Stars: ✭ 407 (+408.75%)
Mutual labels: depth
Retouch
🎬 An OpenGL application for editing and retouching images using depth-maps in 2.5D
Stars: ✭ 63 (-21.25%)
Mutual labels: depth
Monodepth360
Master's project implementing depth estimation for spherical images using unsupervised learning with CNNs.
Stars: ✭ 41 (-48.75%)
Mutual labels: depth
Sfmlearner Pytorch
Pytorch version of SfmLearner from Tinghui Zhou et al.
Stars: ✭ 718 (+797.5%)
Mutual labels: depth
Segment-based Disparity Refinement with Occlusion Handling for Stereo Matching
Please cite the [paper] if you find it useful
@ARTICLE{8661596,
author={T. {Yan} and Y. {Gan} and Z. {Xia} and Q. {Zhao}},
journal={IEEE Transactions on Image Processing},
title={Segment-Based Disparity Refinement With Occlusion Handling for Stereo Matching},
year={2019},
volume={28},
number={8},
pages={3885-3897},
doi={10.1109/TIP.2019.2903318},
ISSN={1057-7149},
month={Aug},}
Workflow
Dependency
-OpenCV 3
-Eigen
Usage
mkdir build
cd build
- on Windows:
cmake .. -G "Visual Studio 15 2017 Win64" -T host=x64
open and compile fdr.sln using Visual Studio 2017
- on Mac & Ubuntu:
cmake ..
make -j4
To run the demo
- on Windows:
double-click demo.bat - on Mac & Ubuntu:
./demo.sh
You will obtain the same results as in our paper on Windows. Results on Mac is silghtly different due to the graph-based segmentation generates different number of superpixels on Mac and Windows.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].