Pose-Invariant Face Alignment with a Single CNN

Abstract

Face alignment has witnessed substantial progress in the last decade. One of the recent focuses has been aligning a dense 3D face shape to face images with large head poses. The dominant technology used is based on the cascade of regressors, e.g., CNN, which has shown promising results. Nonetheless, the cascade of CNNs suffers from several drawbacks, e.g., lack of end-to-end training, hand-crafted features and slow training speed. To address these issues, we propose a new layer, named visualization layer, that can be integrated into the CNN architecture and enables joint optimization with different loss functions. Extensive evaluation of the proposed method on multiple datasets demonstrates state-of-the-art accuracy, while reducing the training time by more than half compared to the typical cascade of CNNs. In addition, we compare multiple CNN architectures with the visualization layer to further demonstrate the advantage of its utilization.

References in corpus (8)

• Deep Residual Learning for Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Stacked Hourglass Networks for Human Pose Estimation
• Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis
• Face Expression Recognition and Analysis: The State of the Art
• HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual Recognition
• A Recurrent Encoder-Decoder Network for Sequential Face Alignment
• Pose-Invariant 3D Face Alignment

Cited by in corpus (9)

• Style Aggregated Network for Facial Landmark Detection
• FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors
• Nonlinear 3D Face Morphable Model
• SFA: Small Faces Attention Face Detector
• Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection
• Adaloss: Adaptive Loss Function for Landmark Localization
• Recurrent Flow-Guided Semantic Forecasting
• Convolutional Point-set Representation: A Convolutional Bridge Between a Densely Annotated Image and 3D Face Alignment
• Joint Face Hallucination and Deblurring via Structure Generation and Detail Enhancement