Iterative $\alpha$-(de)Blending: a Minimalist Deterministic Diffusion Model

Abstract

We derive a minimalist but powerful deterministic denoising-diffusion model. While denoising diffusion has shown great success in many domains, its underlying theory remains largely inaccessible to non-expert users. Indeed, an understanding of graduate-level concepts such as Langevin dynamics or score matching appears to be required to grasp how it works. We propose an alternative approach that requires no more than undergrad calculus and probability. We consider two densities and observe what happens when random samples from these densities are blended (linearly interpolated). We show that iteratively blending and deblending samples produces random paths between the two densities that converge toward a deterministic mapping. This mapping can be evaluated with a neural network trained to deblend samples. We obtain a model that behaves like deterministic denoising diffusion: it iteratively maps samples from one density (e.g., Gaussian noise) to another (e.g., cat images). However, compared to the state-of-the-art alternative, our model is simpler to derive, simpler to implement, more numerically stable, achieves higher quality results in our experiments, and has interesting connections to computer graphics.

References in corpus (14)

• Denoising Diffusion Probabilistic Models
• Hierarchical Text-Conditional Image Generation with CLIP Latents
• Diffusion Models Beat GANs on Image Synthesis
• Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
• Score-Based Generative Modeling through Stochastic Differential Equations
• Generative Modeling by Estimating Gradients of the Data Distribution
• Alias-Free Generative Adversarial Networks
• Elucidating the Design Space of Diffusion-Based Generative Models
• Denoising Diffusion Restoration Models
• Progressive Distillation for Fast Sampling of Diffusion Models
• EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations
• Denoising Diffusion Gamma Models
• Non-Denoising Forward-Time Diffusions
• Heavy-tailed denoising score matching