#371 · Primary category： Computer Vision
RingNet
Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision
Project last updated：03/24/23
GitHub Stars
884
Forks
172
Contributors
5
License
MIT
Why we included this project
RingNet packages the official model from a CVPR 2019 paper that reconstructs a full 3D head mesh from a single face photo, capturing both shape and expression without needing 3D supervision at training time. The repo includes pretrained TensorFlow weights and a clean demo: feed it a loosely cropped face image and get back an .obj mesh, plus optional texture projected from the source photo and the underlying FLAME parameters. Those FLAME outputs are useful beyond the reconstruction itself, since they feed directly into related tools like VOCA for character animation, letting you neutralize expression or reuse the geometry as a template. It is a heavily cited reference implementation for anyone working on face analysis or animation, but keep in mind the environment is dated (Python 2.7, TensorFlow 1.12) and it is really meant for running inference rather than production deployment.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)