Computer Vision 분야 중 하나인 Super Resolution에서 기존 FSRCNN과 FSRCNN-s 모델을 설명하고, 더욱 경량화된 FSRCNN-x 모델을 제안함
기존 ESPCN 모델을 살펴보고, 경량화시킨 Light ESPCN 모델을 제안함.
Super Resolution의 EDSR 모델 소개
SRDenseNet "Image Super-Resolution Using Dense Skip Connections" DenseNet에서 제안되었던 dense block들은 high-level feature들을 추출하기 위해 사용되었고, skip connection들
"Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising"
Neural Blind Deconvolution Using Deep Priors 논문 정리
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
BSRGAN | A blind image slimming model for real image degradation
MPRNet 모델 소개
A Style-Based Generator Architecture for Generative Adversarial Networks 논문 리뷰
Super Resolution for Smartphones <Keywords> Smartphone, Real-time Video Processing, Nyquist Frequency, Super Resolution
BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond
SWAGAN: A Style-based WAvelet-driven Generative Model
MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis