PixelShuffle

2000년 도입 · 논문 45편에서 사용

PixelShuffle is an operation used in super-resolution models to implement efficient sub-pixel convolutions with a stride of $1/r$. Specifically it rearranges elements in a tensor of shape $(\*, C \times r^2, H, W)$ to a tensor of shape $(\*, C, H \times r, W \times r)$. Image Source: Remote Sensing Single-Image Resolution Improvement Using A Deep Gradient-Aware Network with Image-Specific Enhancement

출처: Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network

소개 논문: Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network