Realistic frontal face reconstruction using coupled complementarity of far-near-sighted face images

Highlights：

• A ternary coupled sample pair (LR far-sight frontal face, HR near-sight tilted faces, normal ground truth clear face) training scheme is used to learn the complementary for face fusion.

• A novel secondary relevance attention mechanism enhances the embedding of key features in a progressive manner, with sequential coarse and precise feature matching and embedding. In addition, Scale Entanglement Dense Connectivity Block (SEDCB) is used to progressively integrate relevant information at different scales to enhance the information interaction between tilted surface features.

摘要

•A dual-branch high-resolution frontal face compensation network is proposed, which explicitly exploits the supplementary information of far-near face images in terms of complete facial profile and high-frequency facial details.•A ternary coupled sample pair (LR far-sight frontal face, HR near-sight tilted faces, normal ground truth clear face) training scheme is used to learn the complementary for face fusion.•A novel secondary relevance attention mechanism enhances the embedding of key features in a progressive manner, with sequential coarse and precise feature matching and embedding. In addition, Scale Entanglement Dense Connectivity Block (SEDCB) is used to progressively integrate relevant information at different scales to enhance the information interaction between tilted surface features.

论文评审过程：Received 11 October 2021, Revised 23 February 2022, Accepted 26 April 2022, Available online 27 April 2022, Version of Record 2 May 2022.