SCRN-VRC/YOLOv4-Tiny-in-UnityCG-HLSL
A modern object detector inside fragment shaders
This project helps developers integrate a fast object detection system directly into Unity applications, especially for virtual reality environments like VRChat. It takes a video feed or image as input and outputs the location and type of up to 80 different objects, such as people, cars, or animals. Game developers and VR content creators would use this to add real-time object recognition features to their projects without external machine learning libraries.
No commits in the last 6 months.
Use this if you are a Unity developer looking to embed real-time object detection directly within your game's shaders for low-overhead visual analysis, particularly for VR applications.
Not ideal if you require the highest accuracy or fastest possible object detection performance compared to dedicated machine learning frameworks, or if you are not working within the Unity engine.
Stars
63
Forks
4
Language
C++
License
MIT
Category
Last pushed
Jun 21, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/SCRN-VRC/YOLOv4-Tiny-in-UnityCG-HLSL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
stereolabs/zed-unity
ZED SDK Unity plugin
CMU-Perceptual-Computing-Lab/openpose_unity_plugin
OpenPose's Unity Plugin for Unity users
Unity-Technologies/com.unity.perception
Perception toolkit for sim2real training and validation in Unity
evo-biomech/replicAnt
replicAnt - generating annotated images of animals in complex environments with Unreal Engine
Unity-Technologies/SynthDet
SynthDet - An end-to-end object detection pipeline using synthetic data