An Efficient Network Design for Face Video Super-resolution
Face video super-resolution algorithm aims to reconstruct realistic face details through continuous input video sequences. However, existing video processing algorithms usually contain redundant parameters to guarantee different super-resolution scenes. In this work, we focus on super-resolution of face areas in original video scenes, while rest areas are interpolated. This specific super-resolved task makes it possible to cut redundant parameters in general video super-resolution networks. We construct a dataset consisting entirely of face video sequences for network training and evaluation, and conduct hyper-parameter optimization in our experiments. We use three combined strategies to optimize the network parameters with a simultaneous train-evaluation method to accelerate optimization process. Results show that simultaneous train-evaluation method improves the training speed and facilitates the generation of efficient networks. The generated network can reduce at least 52.4% parameters and 20.7% FLOPs, achieve better performance on PSNR, SSIM compared with state-of-art video super-resolution algorithms. When processing 36x36x1x3 input video frame sequences, the efficient network provides 47.62 FPS real-time processing performance. We name our proposal as hyper-parameter optimization for face Video Super-Resolution (HO-FVSR), which is open-sourced at https://github.com/yphone/efficient-network-for-face-VSR.
Code (0)
등록된 구현이 없습니다.
Tasks
SSIMSuper-ResolutionVideo Super-ResolutionSimilar Papers 제목 키워드 기반
Kalman-Inspired Feature Propagation for Video Face Super-Resolution
Despite the promising progress of face image super-resolution, video face super-resolution remains relatively under-explored. Existing approaches either adapt general video super-resolution networks to face datasets or a…
Image Super-ResolutionSuper-ResolutionVideo Super-ResolutionStyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN
One-shot talking face generation aims at synthesizing a high-quality talking face video from an arbitrary portrait image, driven by a video or an audio segment. One challenging quality factor is the resolution of the out…
Face GenerationFacial EditingMotion GenerationTalking Face Generation+1Unsupervised Learning of Face Representations
We present an approach for unsupervised training of CNNs in order to learn discriminative face representations. We mine supervised training data by noting that multiple faces in the same video frame must belong to differ…
JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution
With the growing importance of preventing the COVID-19 virus, face images obtained in most video surveillance scenarios are low resolution with mask simultaneously. However, most of the previous face super-resolution sol…
DenoisingSuper-ResolutionCubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video
Generating high-quality 360° panoramic videos from perspective input is one of the crucial applications for virtual reality (VR), whereby high-resolution videos are especially important for immersive experience. Existing…
Video Generation