Miscellaneous Components

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

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


Paper Code Results Date Stars


Task Papers Share
Super-Resolution 35 35.00%
Image Super-Resolution 18 18.00%
Video Super-Resolution 8 8.00%
Denoising 2 2.00%
Optical Flow Estimation 2 2.00%
Quantization 2 2.00%
Video Restoration 2 2.00%
Video Enhancement 2 2.00%
Domain Adaptation 1 1.00%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign