Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Torch code for our CVPR 2018 paper "Residual Dense Network for Image Super-Resolution" (Spotlight)
| Date | Stars |
|---|---|
| 2026-07-24 | 563 |
| 2026-07-25 | 563 |
| 2026-07-28 | 563 |
| 2026-07-30 | 563 |
| 2026-08-06 | 563 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Residual Dense Network for Image Super-Resolution This repository is for RDN introduced in the following paper [Yulun Zhang](http://yulunzhang.com/), [Yapeng Tian](http://yapengtian.org/), [Yu Kong](http://www1.ece.neu.edu/~yukong/), [Bineng Zhong](https://scholar.google.de/citations?user=hvRBydsAAAAJ&hl=en), and [Yun Fu](http://www1.ece.neu.edu/~yunfu/), "Residual Dense Network for Image Super-Resolution", CVPR 2018 (spotlight), [[arXiv]](https://arxiv.org/abs/1802.08797) [Yulun Zhang](http://yulunzhang.com/), [Yapeng Tian](http://yapengtian.org/), [Yu Kong](http://www1.ece.neu.edu/~yukong/), [Bineng Zhong](https://scholar.google.de/citations?user=hvRBydsAAAAJ&hl=en), and [Yun Fu](http://www1.ece.neu.edu/~yunfu/), "Residual Dense Network for Image Restoration", arXiv 2018, [[arXiv]](https://arxiv.org/abs/1812.10477) **Visual Results** [[Visual Results@BaiduDrive]](https://pan.baidu.com/s/1jKmu14y), [[Visual Results@GoodleDrive]](https://drive.google.com/file/d/1iXv8pxPz28DmpkUQycZHeKkP1rxReIqN/view?usp=sharing) The code is built on [EDSR (Torch)](https://github.com/LimBee/NTIRE2017) and tested on Ubuntu 14.04 environment (Torch7, CUDA8.0, cuDNN5.1) with Titan X/1080Ti/Xp GPUs. Other implementations: [PyTorch_version](https://github.com/thstkdgus35/EDSR-PyTorch) has been implemented by Nguyễn Trần Toàn ([email protected]) and merged into [EDSR_PyTorch](https://github.com/thstkdgus35/EDSR-PyTorch). [TensorFlow_version](https://github.com/hengchuan/RDN-TensorFlow) by hengchuan. ## Contents 1. [Introduction](#introduction) 2. [Train](#train) 3. [Test](#test) 4. [Results](#results) 5. [Citation](#citation) 6. [Acknowledgements](#acknowledgements) ## Introduction A very deep convolutional neural network (CNN) has recently achieved great success for image super-resolution (SR) and offered hierarchical features as well. However, most deep CNN based SR models do not make full use of the hierarchical features from the original low-resolution (LR) images, thereby achieving relatively-low performance. In this paper, we propose a novel residual dense network (RDN) to address this problem in image SR. We fully exploit the hierarchical features from all the convolutional layers. Specifically, we propose residual dense block (RDB) to extract abundant local features via dense connected convolutional layers. RDB further allows direct connections from the state of preceding RDB to all the layers of current RDB, leading to a contiguous memory (CM) mechanism. Local feature fusion in RDB is then used to adaptively learn more effective features from preceding and current local features and stabilizes the training of wider network. After fully obtaining dense local features, we use global feature fusion to jointly and adaptively learn global hierarchical features in a holistic way. Experiments on benchmark datasets with different degradation models show that our RDN achieves favorable performance against state-of-the-art methods.  Figure 1. Residual dense block (RDB) architecture.  Figure 2. The architecture of our proposed residual dense network (RDN). ## Train ### Prepare training data 1. Download DIV2K training data (800 training + 100 validtion images) from [DIV2K dataset](https://data.vision.ee.ethz.ch/cvl/DIV2K/) or [SNU_CVLab](https://cv.snu.ac.kr/research/EDSR/DIV2K.tar). 2. Place all the HR images in 'Prepare_TrainData/DIV2K/DIV2K_HR'. 3. Run 'Prepare_TrainData_HR_LR_BI/BD/DN.m' in matlab to generate LR images for BI, BD, and DN models respectively. 4. Run 'th png_to_t7.lua' to convert each .png image to .t7 file in new folder 'DIV2K_decoded'. 5. Specify the path of 'DIV2K_decoded' to '-datadir' in 'RDN_TrainCode/code/opts.lua'. For more informaiton, please refer to [EDSR(Torch)](https://github.com/LimBee/NTIRE2017). ### Begin to train 1. (optional) Download models for our paper and place them in '/RDN_TrainCode/experiment/model'. All the models can be downloaded fr
Excerpt of 10,154 characters
Read on GitHub
38
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8901653a3e50aee7, topic:super-resolution, desc:super resolution, readme:super resolution