Accelerating the Super-Resolution Convolutional Neural Network

Code

• github.com/yjn870/FSRCNN-pytorch
  pytorch★ 271
• github.com/Nhat-Thanh/FSRCNN-Pytorch
  pytorch★ 6
• github.com/MohammedAlkhrashi/TMA
  none★ 5
• github.com/GatorSense/SRrootimaging
  pytorch★ 1
• github.com/poikilos/pyrotocanvas
  tf★ 0
• github.com/MindSpore-scientific-2/code-11/tree/main/Super-Resolution-for-Root-Imaging
  mindspore★ 0
• github.com/MohammedAlkhrashi/4D-Dream
  none★ 0
• github.com/MaxHolmberg96/Fast-super-resolution-by-CNN
  tf★ 0
• github.com/Araxeus/PNG-Upscale
  tf★ 0
• github.com/amiq-consulting/image-upscaling-CNN
  none★ 0

Abstract

As a successful deep model applied in image super-resolution (SR), the Super-Resolution Convolutional Neural Network (SRCNN) has demonstrated superior performance to the previous hand-crafted models either in speed and restoration quality. However, the high computational cost still hinders it from practical usage that demands real-time performance (24 fps). In this paper, we aim at accelerating the current SRCNN, and propose a compact hourglass-shape CNN structure for faster and better SR. We re-design the SRCNN structure mainly in three aspects. First, we introduce a deconvolution layer at the end of the network, then the mapping is learned directly from the original low-resolution image (without interpolation) to the high-resolution one. Second, we reformulate the mapping layer by shrinking the input feature dimension before mapping and expanding back afterwards. Third, we adopt smaller filter sizes but more mapping layers. The proposed model achieves a speed up of more than 40 times with even superior restoration quality. Further, we present the parameter settings that can achieve real-time performance on a generic CPU while still maintaining good performance. A corresponding transfer strategy is also proposed for fast training and testing across different upscaling factors.

Tasks

Benchmark Results

Reproductions