Face Mask Extraction in Video Sequence

TL;DR

This paper presents an end-to-end deep learning model combining ConvLSTM and FCN for detailed face mask segmentation in videos, improving accuracy by nearly 17% over baseline models on a challenging dataset.

Contribution

The introduction of a ConvLSTM-FCN model with a novel segmentation loss function for improved face mask extraction in video sequences.

Findings

Achieved 16.99% relative improvement in mean IoU over baseline.

Effectively models temporal correlations in video for better segmentation.

Specialized models for face, eyes, and mouth regions enhance accuracy.

Abstract

Inspired by the recent development of deep network-based methods in semantic image segmentation, we introduce an end-to-end trainable model for face mask extraction in video sequence. Comparing to landmark-based sparse face shape representation, our method can produce the segmentation masks of individual facial components, which can better reflect their detailed shape variations. By integrating Convolutional LSTM (ConvLSTM) algorithm with Fully Convolutional Networks (FCN), our new ConvLSTM-FCN model works on a per-sequence basis and takes advantage of the temporal correlation in video clips. In addition, we also propose a novel loss function, called Segmentation Loss, to directly optimise the Intersection over Union (IoU) performances. In practice, to further increase segmentation accuracy, one primary model and two additional models were trained to focus on the face, eyes, and mouth regions, respectively. Our experiment shows the proposed method has achieved a 16.99% relative improvement (from 54.50% to 63.76% mean IoU) over the baseline FCN model on the 300 Videos in the Wild (300VW) dataset.