Image Generation Models

Diffusion

Introduced by Ho et al. in Denoising Diffusion Probabilistic Models

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 Models

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Denoising 84 16.80%
Image Generation 61 12.20%
Time Series 16 3.20%
Semantic Segmentation 12 2.40%
Super-Resolution 11 2.20%
Text-to-Image Generation 9 1.80%
Image Inpainting 9 1.80%
BIG-bench Machine Learning 8 1.60%
Decision Making 7 1.40%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories