Rumen Filkov's starred repositories
PatchFusion
[CVPR 2024] An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation
unity-barracuda-inference-base
This Unity package provides a foundation for performing inference with the Barracuda inference library. It includes a flexible base class to extend with task-specific packages.
super-gradients
Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.
unity-barracuda-inference-yolox
This Unity package extends the functionality of the barracuda-inference-base package to perform object detection using YOLOX models.
Dependencies
A rewrite of the old legacy software "depends.exe" in C# for Windows devs to troubleshoot dll load dependencies issues.
sentis-samples
Sentis samples internal development repository. Contains example and template projects for Sentis package use.
monodepth2
[ICCV 2019] Monocular depth estimation from a single image
mmsegmentation
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
Monocular-Depth-Estimation-Toolbox
Monocular Depth Estimation Toolbox based on MMSegmentation.
OrbbecSDK-K4A-Wrapper
This repo is forked from Azure-kinect-Sensor-SDK,contain the K4A wrapper for OrbbecSDK.
torchsparse
[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.
open-interpreter
A natural language interface for computers
sharp-transformers
A Unity plugin for using Transformers models in Unity.
UnityGaussianSplatting
Toy Gaussian Splatting visualization in Unity
TalkomicApp-Unity
Whisper, Stable Diffusion on U-Net, Chatgpt AI models, bundled in a Unity project. Locally run models powered by Onnxruntime. These transcribe podcasts' audio to text and generate contextual images tied to the transcribed text.
replit-3B-inference
Run inference on replit-3B code instruct model using CPU
VuforiaStandaloneBuild
Demo PC builds with Vuforia plugin
FastOnnxLoader
Loads in onnx files with less RAM
AdelaiDepth
This repo contains the projects: 'Virtual Normal', 'DiverseDepth', and '3D Scene Shape'. They aim to solve the monocular depth estimation, 3D scene reconstruction from single image problems.
ailia-models
The collection of pre-trained, state-of-the-art AI models for ailia SDK