Deep attentive pixels for face super-resolution
Krit Duangprom, Sovann Chen, Supavadee Aramvith · International Workshop on Advanced Imaging Technology (IWAIT) 2022 · 2022
Face super-resolution, successfully using fusion network approach, has successfully solved the problem of face image restoration. Recently, face attributes have been effectively used to guide the low-level feature point of the face to perform viable face recovery. First, the low-resolution image is enlarged into a super-resolution face image. Landmarks are estimated to guide the network to enhance the super-resolution image repeatedly. However, the face super-resolution network architecture parameter is redundant, and the learning efficiency is low on mapping input and target output. This paper proposes a deep attention pixel for face super-resolution, which applies an attention mechanism to optimize feature extraction and fuses the channel attention with facial landmarks heatmaps. Experimental results demonstrate that the proposed method achieves higher performance than other state-of-the-art face super-resolution methods.