6DoF Object detection and tracking in web browser – WebAR.rocks.train
6DoF Object Detection and Tracking in JavaScript/WebGL. A neural network is trained in the web browser using a 3D model rendered with ThreeJS. Then, the trained model is used for augmented reality with React Three Fiber. WebAR.rocks.train is released under the MIT License on GitHub.
6DoF Object detection and tracking in web browser – WebAR.rocks.train launched on March 11, 2025 with 12 votes, #2,041 of 7,215 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 1 year on.
In plain words
WebAR.rocks.train enables 6DoF object detection and tracking directly in web browsers using JavaScript and WebGL. Users can train a neural network by rendering 3D models with ThreeJS, then deploy the trained model for augmented reality applications built with React Three Fiber. The tool operates entirely in-browser, eliminating the need for external training infrastructure, and is available as open-source software under the MIT License on GitHub.
written from the facts on this page · September 2026
From the sources
Object detection, tracking, and 6DoF pose estimation in the web browser, integrated training environment to train your own neural network models 🚀 - WebAR-rocks/WebAR.rocks.train
Does a similar job
all alternatives →
Building a web search engine from scratch with 3B neural embeddings2025 · blog.wilsonl.in · ▲699End-to-end deep dive of the project, spanning a large GPU cluster, distributed RocksDB, and terabytes of sharded HNSW.
- GAGPU-Accelerated Digit Recognition with WebGL2016 · erkaman.github.io · ▲135
- UDUsing deep learning to detect objects from your webcam2018 · modeldepot.github.io · ▲95
Watch a neural net learn to play SnakeMay 2026 · ppo.gradexp.xyz · ▲205In browser PPO training demo, made possible by tinygrad: TinyJit -> WebGPU kernels. Requires WebGPU.
TensorSpace.js – Neural network 3D visualization framework2018 · github.com · ▲167Neural network 3D visualization framework, build interactive and intuitive model in browsers, support pre-trained deep learning models from TensorFlow, Keras, TensorFlow.js - GitHub - tensorspace-team/tensorspace: Neural network 3D visualization framework, build interactive and intuitive model in br
- ATA tiny JS library for real-time localization of eye pupils2019 · tehnokv.com · ▲153
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗
Launched alongside, March 2025
the whole month →
Mimic Human Research & Save Findings in AI Knowledge Base
AI · 2025 · sider.ai
