Optimized Linear Measurements for Inverse Problems using Diffusion-Based Image Generation

LQ Zhang, Z Kadkhodaie, E P Simoncelli and D H Brainard.

arXiv.org e-prints, Technical Report 2405.17456, May 2024.

DOI: 10.48550/arXiv.2405.17456

This paper has been superseded by:
Generalized compressed sensing for image reconstruction with diffusion probabilistic models
LQ Zhang, Z Kadkhodaie, E P Simoncelli and D H Brainard.
Trans. Machine Learning Research, May 2025. To appear.

We re-examine the problem of reconstructing a high-dimensional signal from a small set of linear measurements, in combination with image prior from a diffusion probabilistic model. Well-established methods for optimizing such measurements include principal component analysis (PCA), independent component analysis (ICA) and compressed sensing (CS), all of which rely on axis- or subspace-aligned statistical characterization. But many naturally occurring signals, including photographic images, contain richer statistical structure. To exploit such structure, we introduce a general method for obtaining an optimized set of linear measurements, assuming a Bayesian inverse solution that leverages the prior implicit in a neural network trained to perform denoising. We demonstrate that these measurements are distinct from those of PCA and CS, with significant improvements in minimizing squared reconstruction error. In addition, we show that optimizing the measurements for the SSIM perceptual loss leads to perceptually improved reconstruction. Our results highlight the importance of incorporating the specific statistical regularities of natural signals when designing effective linear measurements.
  • Listing of all publications