Changes between Version 8 and Version 9 of SponsoringPrograms/GSoC/2018/Results

Aug 9, 2018, 4:32:28 PM (10 months ago)



  • SponsoringPrograms/GSoC/2018/Results

    v8 v9  
    3535''Corrected by Weighted Grey Edge:''[[BR]]
     38== Super Resolution filter ==
     40'''Description:''' Super resolution methods aim to recover high-resolution images from low-resolution images. These methods find direct application in many areas such as medical imaging, security and surveillance imaging, HDTV, satellite imaging. This project goal was to implement machine-learning-based super-resolution upscaling filter.
     42'''Results:''' The basis of this project was the result of the qualification task implementing [[ | SRCNN]] model for image super-resolution ([[ | commit]]). Contributions of the GSoC period include:
     43* Introduction of DNN inference module ([[ | commit]]). This module includes interface for model loading and execution as well as simple backend, which supports layers required for the super resolution filter.
     44* Introduction of [[ | TensorFlow]] backend to DNN inference module ([[ | commit]]). It implements backend executing binary [[ | TensorFlow]] models using [[ | TensorFlow]] framework.
     45* Implementation of [[ | ESPCN]] model for super resolution ([[ | commit]]). This model shows better results in terms of restoration accuracy and speed.
     46* Various improvements and fixes of the DNN module and the super resolution filter. Commits: [[ | 1]], [[ | 2]], [[ | 3]], [[ | 4]], [[ | 5]].
     47Scripts for model training and evaluation as well as generation of model files, suitable for the super resolution filter, are provided in the [[ | repository]]. In addition to [[ | SRCNN]] and [[ | ESPCN]] models, [[ | VESPCN]] and [[ | VSRNet]] models were trained and evaluated, but they were not implemented in the super resolution filter due to low increase in restoration accuracy.
     49'''Future work:''' After the GSoC period resnet-based models will be evaluated. If their upscaling quality is good, one of them will be added to the super resolution filter.
     51'''Mentor:''' Pedro Souza (bygrandao AT gmail DOT com)
     53'''Student:''' Sergey Lavrushkin (dualfal AT gmail DOT com)