Dmitry Ulyanov personal blog
Deep image prior 'learns' on just one image
Deep convolutional networks have become a popular tool for image generation and restoration. Generally, their excellent performance is imputed to their ability to learn realistic image priors from a large number of example images. In this paper, we show that, on the contrary, the structure of a generator network is…
- Points
- 782
- HN comments
- 223
- Submissions
- 1
- Cited by
- 4 commenters
AI & Machine LearningMath & Algorithms2017
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Nov 30, 2017 | Deep image prior 'learns' on just one image by singularity2001 | 782 | 223 |
Cited in comments
Linked from 4 Hacker News comments by 4 different people, from Dec 2017 to Aug 2022.
Most recent:
- YetAnotherNick · Aug 20, 2022
- fwilliams · Jul 21, 2018
- gwern · Jul 10, 2018
- arnioxux · Dec 29, 2017
