AI models
DnCNN
Published
Feb 1, 2017
DnCNN is an AI model developed by Harbin Institute of Technology, Hong Kong Polytechnic University, ULSee Inc. and Xi’an Jiaotong University (China and Hong Kong), first published in February 2017. It works in the vision and image generation domain, on tasks such as image super-resolution.
Epoch AI has no training-compute estimate for this model. It was trained on roughly 2.6B datapoints.
The reference paper has 7,779 citations.
Full record
- Organization
- Harbin Institute of Technology, Hong Kong Polytechnic University, ULSee Inc., Xi’an Jiaotong University
- Country of organization
- China, Hong Kong
- Domain
- Vision, Image generation
- Task
- Image super-resolution
- Dataset size
- 2.6B
- Citations
- 7,779
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models