A5088406264- Advanced Image Processing Techniques
- Advanced Vision and Imaging
- Data Stream Mining Techniques
- Time Series Analysis and Forecasting
- Image Processing Techniques and Applications
- Digital Holography and Microscopy
- Machine Learning and Data Classification
- Image and Signal Denoising Methods
Duke University
2018-2020
This paper reviews the 2nd NTIRE challenge on single image super-resolution (restoration of rich details in a low resolution image) with focus proposed solutions and results. The had 4 tracks. Track 1 employed standard bicubic downscaling setup, while Tracks 2, 3 realistic unknown downgrading operators simulating camera acquisition pipeline. were learnable through provided pairs high train images. tracks 145, 114, 101, 113 registered participants, resp., 31 teams competed final testing...
This work identifies and addresses two important technical challenges in single-image super-resolution: (1) how to upsample an image without magnifying noise (2) preserve large scale structure when upsampling. We summarize the techniques we developed for our second place entry Track 1 (Bicubic Downsampling), seventh 2 (Realistic Adverse Conditions), 3 difficult) 2018 NTIRE Super-Resolution Challenge. Furthermore, present new neural network architectures that specifically address listed...
This work identifies and addresses two important technical challenges in single-image super-resolution: (1) how to upsample an image without magnifying noise (2) preserve large scale structure when upsampling. We summarize the techniques we developed for our second place entry Track 1 (Bicubic Downsampling), seventh 2 (Realistic Adverse Conditions), 3 difficult) 2018 NTIRE Super-Resolution Challenge. Furthermore, present new neural network architectures that specifically address listed...