Search Results for author: Hanwen Liu

Found 8 papers, 4 papers with code

Back-Projection Pipeline

no code implementations25 Jan 2021 Pablo Navarrete Michelini, Hanwen Liu, Yunhua Lu, Xingqun Jiang

We propose a simple extension of residual networks that works simultaneously in multiple resolutions.

Rain Removal Super-Resolution

Multi-Grid Back-Projection Networks

no code implementations1 Jan 2021 Pablo Navarrete Michelini, Wenbin Chen, Hanwen Liu, Dan Zhu, Xingqun Jiang

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.

MGBPv2: Scaling Up Multi-Grid Back-Projection Networks

1 code implementation27 Sep 2019 Pablo Navarrete Michelini, Wenbin Chen, Hanwen Liu, Dan Zhu

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

Multi-Scale Recursive and Perception-Distortion Controllable Image Super-Resolution

1 code implementation27 Sep 2018 Pablo Navarrete Michelini, Dan Zhu, Hanwen Liu

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

Multigrid Backprojection Super-Resolution and Deep Filter Visualization

1 code implementation25 Sep 2018 Pablo Navarrete Michelini, Hanwen Liu, Dan Zhu

It is also residual since we use the network to update the outputs of a classic upscaler.

Super-Resolution

Convolutional Networks with MuxOut Layers as Multi-rate Systems for Image Upscaling

no code implementations22 May 2017 Pablo Navarrete Michelini, Hanwen Liu

We interpret convolutional networks as adaptive filters and combine them with so-called MuxOut layers to efficiently upscale low resolution images.

Cannot find the paper you are looking for? You can Submit a new open access paper.