learn-optimizer-rgdn

August 17, 2020 · View on GitHub

Learning Deep Gradient Descent Optimization for Image Deconvolution

Dong Gong*, Zhen Zhang*, Qinfeng Shi, Anton van den Hengel, Chunhua Shen, Yanning Zhang (*Equal contribution)

In IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2020.

This implementation is for non-commercial research use only. If you find this code useful in your research, please cite the above paper.

Testing script: ./test_entry.py.
Pretrained model: ./rgdn.tr.
Testing Examples, with real and synthetic images.
Kernel generation in Python: ./data/make_kernel.py, a Python implementation of the kernel simulation method from "A. Chakrabarti, A neural approach to blind motion deblurring, in ECCV, 2016".

Requirements