themancalledjakob's Stars
zylon-ai/private-gpt
Interact with your documents using the power of GPT, 100% privately, no data leaks
ungoogled-software/ungoogled-chromium
Google Chromium, sans integration with Google
evilsocket/opensnitch
OpenSnitch is a GNU/Linux interactive application firewall inspired by Little Snitch.
NVlabs/stylegan3
Official PyTorch implementation of StyleGAN3
pixelfed/pixelfed
Photo Sharing. For Everyone.
wjakob/instant-meshes
Interactive field-aligned mesh generator
input-leap/input-leap
Open-source KVM software
httptoolkit/httptoolkit
HTTP Toolkit is a beautiful & open-source tool for debugging, testing and building with HTTP(S) on Windows, Linux & Mac :tada: Open an issue here to give feedback or ask for help.
NVlabs/nvdiffrec
Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and Lighting From Images".
panique/huge
Simple user-authentication solution, embedded into a small framework.
foliojs/fontkit
An advanced font engine for Node and the browser
ands/lightmapper
A C/C++ single-file library for drop-in lightmap baking. Just use your existing OpenGL renderer to bounce light!
Scony/godot-gdscript-toolkit
Independent set of GDScript tools - parser, linter, formatter, and more
hannorein/rebound
đź’« An open-source multi-purpose N-body code.
arkq/bluez-alsa
Bluetooth Audio ALSA Backend
FORTH-ModelBasedTracker/MocapNET
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
rgl-epfl/differentiable-sdf-rendering
Source code for "Differentiable Signed Distance Function Rendering" (Siggraph 2022)
alex04072000/FuSta
Hybrid Neural Fusion for Full-frame Video Stabilization
habamax/vim-godot
Use vim and godot engine to make games
Unity-Technologies/vscode-unity-debug
Unity debugging support for VS Code
Torsion-Audio/Scyclone
Real-time Neural Timbre Transfer
antimodular/Best-practices-for-conservation-of-media-art
Best practices for conservation of media art from an artist’s perspective
Aradhye2002/EcoDepth
[CVPR'2024] Official implementation of the paper "ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation"
dtamayo/reboundx
A library for adding additional forces to the REBOUND N-body integration package
codeape2/vim-multiple-monitors
Multiple monitor support for vim.
daitomanabe/Human-Pose-and-Motion
Human-Pose-and-Motion History
hannorein/megaconstellations
Script to reproduce figures of Lawler, Boley & Rein 2021. Source code of web app.
jeremysalwen/Minicomputer-LV2
LV2 port of Minicomputer (plus more?)
NaN-xyz/GlyphsApp-Scripts
GlyphsApp Scripts
NaN-xyz/GlyphsApp-Filters