Training a denoiser on signals gives you a powerful prior over this signal that you can then use to sample examples of this signal.
Source: Generative Modeling by Estimating Gradients of the Data DistributionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Denoising | 39 | 46.99% |
Image Generation | 11 | 13.25% |
Time Series Forecasting | 3 | 3.61% |
Translation | 2 | 2.41% |
Super-Resolution | 2 | 2.41% |
Time Series Analysis | 2 | 2.41% |
Density Estimation | 2 | 2.41% |
Image Inpainting | 2 | 2.41% |
Conditional Image Generation | 1 | 1.20% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |