Raymondmax/SR_Framework

A generic framework which implements all famouts super-resolution models

Python

SR_Framework

A generic super-resolution framework which implements the following networks (Updating...)

LatticeNet [ECCV2020]
IMDN [ACM MM2019]
SRFBN [CVPR2019]
IDN [CVPR2018]
CARN [ECCV2018]
EDSR [CVPR2017]
DRRN [CVPR2017]
LapSRN [CVPR2017]
DRCN [CVPR2016]
VDSR [CVPR2016]

Implement some useful functions for article figures. Like the following:

1. generate_best: Automatically compare your method with other methods and visualize the best patches.

2. Frequency_analysis: Convert an image to 1-D spectral densities.

3. relation: Explore relations in fuse stage.(eg. torch.cat([t1, t2, t3, c4], dim=1) and then fuse them with 1x1 convolution)

4. feature_map: Visualize feature map.(average feature maps along channel axis)