Effect of Visual Context Information for Super Resolution Problems

In this study, the effect of visual context information to the performance of learning-based techniques for the super resolution problem is analyzed. Beside the interpretation of the experimental results in detail, its theoretical reasoning is also achieved in the paper. For the experiments, two different visual datasets composed of natural and remote sensing scenes are utilized. From the experimental results, we observe that keeping visual context information in the course of parameter learning for convolutional neural networks yields better performance compared to the baselines. Moreover, we summarize that finetuning pre-trained parameters with the related context yet fewer samples improves the results.

• Publication year

  2019

• Venue

  Signal Processing and Communications Applications Conference

• Publication date

  2019-04-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/SIU.2019.8806598
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Example-Based Super Resolution

  2016cited by this paper
• Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network

  2016influential reference
• Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

  2016influential reference
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

  2015cited by this paper
• Image Super-Resolution Using Deep Convolutional Networks

  2014influential reference
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Gradient Profile Prior and Its Applications in Image Super-Resolution and Enhancement

  2011cited by this paper
• New motion compensation model via frequency classification for fast video super-resolution

  2009cited by this paper
• Super Resolution With Probabilistic Motion Estimation

  2009cited by this paper
• SoftCuts: A Soft Edge Smoothness Prior for Color Image Super-Resolution

  2009cited by this paper
• Fast image/video upsampling

  2008cited by this paper
• Image Super-Resolution by TV-Regularization and Bregman Iteration

  2008cited by this paper
• Image super-resolution using gradient profile prior

  2008cited by this paper
• Image upsampling via imposed edge statistics

  2007cited by this paper
• Soft Edge Smoothness Prior for Alpha Channel Super Resolution

  2007cited by this paper
• A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics

  2001cited by this paper
• Image magnification using level-set reconstruction

  2001cited by this paper
• Limits on super-resolution and how to break them

  2000cited by this paper
• Motion Analysis for Image Enhancement: Resolution, Occlusion, and Transparency

  1993cited by this paper

• No citing papers are available for this paper.