Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound (https://arxiv.org/abs/2006.11239).
Source: Denoising Diffusion Probabilistic ModelsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Generation | 94 | 13.43% |
Denoising | 81 | 11.57% |
Text-to-Image Generation | 25 | 3.57% |
Video Generation | 16 | 2.29% |
Language Modelling | 13 | 1.86% |
Super-Resolution | 12 | 1.71% |
Decoder | 12 | 1.71% |
3D Generation | 11 | 1.57% |
Semantic Segmentation | 10 | 1.43% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |