Face Mask Extraction in Video Sequence
This work addresses the problem of detailed facial component segmentation in videos for applications like video analysis and human-computer interaction, representing an incremental advancement over existing methods.
The paper tackles face mask extraction in video sequences by introducing an end-to-end trainable model that integrates Convolutional LSTM with Fully Convolutional Networks and a novel Segmentation Loss, achieving a 16.99% relative improvement in mean IoU from 54.50% to 63.76% on the 300VW dataset.
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.