#399 · Primary category： Computer Vision
2D-and-3D-face-alignment
This repository implements a demo of the networks described in "How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)" paper.
Project last updated：02/26/18
GitHub Stars
973
Forks
208
Contributors
3
License
Other
Why we included this project
Anyone tracing how computer vision moved from 2D landmarks to full 3D face meshes should look here: this is the code behind the paper "How far are we from solving the 2D & 3D Face Alignment problem?", which introduced a dataset of 230,000 3D facial landmarks. The repo includes a runnable demo of the FAN-style network that takes a single image and predicts 2D landmarks plus the full face geometry, with setup notes and a link to a separate training codebase. It is a compact reference model for pose or landmark experiments, easier to follow than today's larger face libraries. The catch is the stack: Torch7 and Python 2.7, so plan on wrestling with legacy dependencies if you actually want to run it.
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)