| zk00006/OpenTLD |
2,070 |
|
0 |
0 |
about 10 years ago |
0 |
|
38 |
gpl-3.0 |
Matlab |
| OpenTLD is an open source library for real-time 2D tracking of a single object in video. This repository is no longer under development. For latest version see: http://www.tldvision.com/tld2.html |
| johnBuffer/AntSimulator |
1,966 |
|
0 |
0 |
over 3 years ago |
0 |
|
21 |
mit |
C++ |
| Simple Ants simulator |
| Inochi2D/inochi2d |
1,117 |
|
0 |
2 |
about 2 years ago |
9 |
August 11, 2023 |
10 |
bsd-2-clause |
D |
| Inochi2D reference implementation aimed at rendering 2D puppets that can be animated in real-time (using eg. facial capture). |
| nCine/nCine |
950 |
|
0 |
0 |
about 2 years ago |
0 |
|
2 |
mit |
C++ |
| A cross-platform 2D game engine |
| FORTH-ModelBasedTracker/MocapNET |
738 |
|
0 |
0 |
over 2 years ago |
0 |
|
16 |
other |
C++ |
| We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance |
| danchitnis/webgl-plot |
473 |
|
0 |
7 |
over 2 years ago |
41 |
August 27, 2023 |
4 |
mit |
TypeScript |
| A high-Performance real-time 2D plotting library based on native WebGL |
| buptxyb666/AdaptivePose |
168 |
|
0 |
0 |
over 2 years ago |
0 |
|
8 |
mit |
Jupyter Notebook |
| This is an official implementation of our AAAI2022 paper AdaptivePose and Arxiv paper AdaptivePose++ |
| bardiadoosti/HOPE |
135 |
|
0 |
0 |
over 5 years ago |
0 |
|
5 |
|
Python |
| Source code of CVPR 2020 paper, "HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation" |
| verse/verse |
111 |
|
0 |
0 |
almost 9 years ago |
0 |
|
14 |
other |
C |
| Network protocol for real-time sharing between graphical applications |
| Blotch3D/Blotch3D |
85 |
|
0 |
0 |
about 2 years ago |
8 |
April 17, 2023 |
0 |
other |
C# |
| A high-level 3D class library that gives you real-time 3D graphics with just a few lines of C# code. Supports multiple platforms. Implemented as a .NET Standard library that works with all versions of .NET. See 'Quick start for Windows' to get started. Also available as a NuGet package without the examples or source. |
