img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7613-7623
Abstract
We propose real-time, six degrees of freedom (6DoF), 3D face pose estimation without face detection or landmark localization. We observe that estimating the 6DoF rigid transformation of a face is a simpler problem than facial landmark detection, often used for 3D face alignment. In addition, 6DoF offers more information than face bounding box labels. We leverage these observations to make multiple contributions: (a) We describe an easily trained, efficient, Faster R-CNN–based model which regresses 6DoF pose for all faces in the photo, without preliminary face detection. (b) We explain how pose is converted and kept consistent between the input photo and arbitrary crops created while training and evaluating our model. (c) Finally, we show how face poses can replace detection bounding box training labels. Tests on AFLW2000-3D and BIWI show that our method runs at real-time and outperforms state of the art (SotA) face pose estimators. Remarkably, our method also surpasses SotA models of comparable complexity on the WIDER FACE detection benchmark, despite not been optimized on bounding box labels.Keywords
All Related Versions
This publication has 55 references indexed in Scilit:
- Face Alignment by Explicit Shape RegressionInternational Journal of Computer Vision, 2013
- Viewing Real-World Faces in 3D2013
- 300 Faces in-the-Wild Challenge: The First Facial Landmark Localization Challenge2013
- Deep Convolutional Network Cascade for Facial Point Detection2013
- Random Forests for Real Time 3D Face AnalysisInternational Journal of Computer Vision, 2012
- EPnP: An Accurate O(n) Solution to the PnP ProblemInternational Journal of Computer Vision, 2008
- Histograms of Oriented Gradients for Human Detection2005
- Robust Real-Time Face DetectionInternational Journal of Computer Vision, 2004
- Active appearance models1998
- Model-based object pose in 25 lines of codeInternational Journal of Computer Vision, 1995