DnCNN

Closed weights Harbin Institute of Technology,Hong Kong Polytechnic University,ULSee Inc.,Xi’an Jiaotong University February 2017

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Harbin Institute of Technology,Hong Kong Polytechnic University,ULSee Inc.,Xi’an Jiaotong University
Organisation type
Academia,Academia,Industry,Academia
Country
China, Hong Kong
Published
1 February 2017
Authors
Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, Lei Zhang

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Vision, Image generation
Task
Image super-resolution

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Training data
2,560,000,000 tokens

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked
Highly cited
Record confidence
Unknown
Citations
7,779

Sources

Where this record came from and when it was last checked.

Reference
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Last updated
1 January 2026

What the numbers mean

What this model is

DnCNN was published by Harbin Institute of Technology,Hong Kong Polytechnic University,ULSee Inc.,Xi’an Jiaotong University, in China, in February 2017. academia,Academia,Industry,Academia is the category the publisher falls under.

It works in Vision, Image generation, and is recorded as doing image super-resolution.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

What went into building it

The training set ran to roughly 2,560,000,000 tokens.

The reason it appears in this catalogue at all is highly cited.

Answers

DnCNN — common questions

01

Is DnCNN open source?

The licensing for DnCNN was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

02

How many parameters does DnCNN have?

No parameter count has been published for DnCNN, which is why no memory or speed figure appears on this page.

03

Who created DnCNN?

DnCNN was published by Harbin Institute of Technology,Hong Kong Polytechnic University,ULSee Inc.,Xi’an Jiaotong University, based in China, categorised as academia,Academia,Industry,Academia.

04

When was DnCNN released?

DnCNN was published in February 2017. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is DnCNN used for?

DnCNN works in Vision, Image generation, and is recorded as handling image super-resolution. These are the areas it was designed around; they describe intent rather than a hard boundary.

06

What GPU do I need to run DnCNN?

None. DnCNN is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

Source

Original publication

Record last updated 1 January 2026

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.