Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Workshop on Machine Learning and Compression

Towards Scalable Compression with Universally Quantized Diffusion Models

Yibo Yang · Justus C. Will · Stephan Mandt


Abstract:

Diffusion probabilistic models have achieved success in many generative modeling tasks, from image generation to inverse problem solving.A distinct feature of these models is that they correspond to deep hierarchical latent variable models optimizing a variational evidence lower bound (ELBO) on the data likelihood.Drawing on a basic connection between likelihood modeling and compression, we explore the potential of diffusion models for progressive coding, resulting in a sequence of bits that can be incrementally transmitted and decoded with progressively improving reconstruction quality.Unlike prior work based on Gaussian diffusion or conditional diffusion models, we propose a new form of diffusion model with uniform noise in the forward process, whose negative ELBO corresponds to the end-to-end compression cost using universal quantization.We obtain promising first results on image compression, achieving competitive rate-distortion and rate-realism results on a wide range of bit-rates with a single model.

Chat is not available.