For this target we propose a strategy using noise inputs in different resolution scales to control the amount of artificial details generated in the output.
Then, anchor-based 3D convolution is adopted to aggregate these anchors' features to the core points.
Here, we describe our solution for the AIM-2019 Extreme Super-Resolution Challenge, where we won the 1st place in terms of perceptual quality (MOS) similar to the ground truth and achieved the 5th place in terms of high-fidelity (PSNR).
Image and Video Processing
We describe our solution for the PIRM Super-Resolution Challenge 2018 where we achieved the 2nd best perceptual quality for average RMSE<=16, 5th best for RMSE<=12. 5, and 7th best for RMSE<=11. 5.
Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Signal Processing
We interpret convolutional networks as adaptive filters and combine them with so-called MuxOut layers to efficiently upscale low resolution images.