Apr 16, 2018 · Abstract:Deep convolutional neural networks (DCNN) have been widely adopted for research on super resolution recently, however previous work ...
Single image super resolution (SISR) has been one of the classic ill-posed problems of image restoration, it tries to reconstruct a high resolution (HR) image ...
A new perspective regarding to image restoration problems is presented that one can construct the neural network model reflecting the physical significance ...
RDB consists dense connected layers and local feature fu- sion (LFF) with local residual learning (LRL). Our RDB also support contiguous memory among RDBs. The ...
In this paper, we propose a deep residual dense network (DRDN) for single image super-resolution. Based on human perceptual characteristics.
A list of resources for example-based single image super-resolution, inspired by Awesome-deep-vision and Awesome Computer Vision.
The residual dense network (RDN) [14] innovatively combined residual learning and dense connection to fully utilize both the shallow features and deep features ...
We have introduced the dilated residual dense neural network to accelerate the speed of deep networks for image super-resolution.
People also ask
What is super-resolution network?
What is the difference between single image and multi image super-resolution?
What are the applications of single image super-resolution?
What are residual networks for image classification?
Abstract. Plenoptic cameras usually sacrifice the spatial resolution of their SAIs to acquire geometry information from different viewpoints.
Comprehensive experiments demonstrate the necessity of our RFA framework and the superiority of our RFANet over state-of-the-art SISR methods. 1. Introduction.