shamangary/FSA-Net
A deep learning model for estimating head pose angles (yaw, pitch, roll) from single facial images.
Not currently ranked — collecting fresh signals.
star history
FSA-Net is a CVPR 2019 neural network that estimates head pose from a single image by learning fine-grained structure aggregation of facial features. Implemented in TensorFlow and Keras, it achieves state-of-the-art results on benchmarks such as AFLW2000. The repository includes webcam demo code using SSD face detection for real-time inference.
Frequently asked
- What is shamangary/FSA-Net?
- A deep learning model for estimating head pose angles (yaw, pitch, roll) from single facial images.
- Is FSA-Net open source?
- Yes — shamangary/FSA-Net is open source, released under the Apache-2.0 license.
- What language is FSA-Net written in?
- shamangary/FSA-Net is primarily written in Python.
- How popular is FSA-Net?
- shamangary/FSA-Net has 632 stars on GitHub.
- Where can I find FSA-Net?
- shamangary/FSA-Net is on GitHub at https://github.com/shamangary/FSA-Net.