Denoising diffusion probabilistic models

Objectives:

• Develop novel methods of inverse problem solutions based on denoising diffusion probabilistic models
• Investigate new approaches to uncertainty estimation based on stochasticity of denoising diffusion models
• Introduce new techniques of conditional generation based on concatenation, cross-attention and bias

Expected Results:

• Efficient solution of inverse problems and comparison with the state of the art based on other generative models
• Usage of stochasticity for the uncertainty estimation
• Minimization of inference complexity with the preservation of accuracy