Composite recurrent network with internal denoising for facial alignment in still and video images in the wild

作者：

Highlights：

• Unified approach to solve both single and multi frame facial alignment.

• Variable length temporal modeling of frame sequences using multi-layer LSTM.

• The use of Internal denoiser on training enhancing intermediate image lead to more accurate estimates.

• States of the art results on both Single Image Facial Alignment and Deformable Facial Tracking.

摘要

•Unified approach to solve both single and multi frame facial alignment.•Variable length temporal modeling of frame sequences using multi-layer LSTM.•The use of Internal denoiser on training enhancing intermediate image lead to more accurate estimates.•States of the art results on both Single Image Facial Alignment and Deformable Facial Tracking.

论文关键词：Facial alignment,Facial tracking,Temporal modeling,Internal denoising

论文评审过程：Received 21 October 2019, Revised 20 November 2020, Accepted 21 April 2021, Available online 26 April 2021, Version of Record 7 May 2021.

论文官网地址：https://doi.org/10.1016/j.imavis.2021.104189