Uncertainty Quantification in HSI Reconstruction using Physics-Aware Diffusion Priors and Optics-Encoded Measurements
By: Juan Romero , Qiang Fu , Matteo Ravasi and more
Potential Business Impact:
Makes blurry pictures of light colors sharp again.
Hyperspectral image reconstruction from a compressed measurement is a highly ill-posed inverse problem. Current data-driven methods suffer from hallucination due to the lack of spectral diversity in existing hyperspectral image datasets, particularly when they are evaluated for the metamerism phenomenon. In this work, we formulate hyperspectral image (HSI) reconstruction as a Bayesian inference problem and propose a framework, HSDiff, that utilizes an unconditionally trained, pixel-level diffusion prior and posterior diffusion sampling to generate diverse HSI samples consistent with the measurements of various hyperspectral image formation models. We propose an enhanced metameric augmentation technique using region-based metameric black and partition-of-union spectral upsampling to expand training with physically valid metameric spectra, strengthening the prior diversity and improving uncertainty calibration. We utilize HSDiff to investigate how the studied forward models shape the posterior distribution and demonstrate that guiding with effective spectral encoding provides calibrated informative uncertainty compared to non-encoded models. Through the lens of the Bayesian framework, HSDiff offers a complete, high-performance method for uncertainty-aware HSI reconstruction. Our results also reiterate the significance of effective spectral encoding in snapshot hyperspectral imaging.
Similar Papers
Hyperspectral Image Generation with Unmixing Guided Diffusion Model
CV and Pattern Recognition
Makes fake pictures that look like real, colorful light.
SpectralAdapt: Semi-Supervised Domain Adaptation with Spectral Priors for Human-Centered Hyperspectral Image Reconstruction
CV and Pattern Recognition
Lets doctors see hidden details in body scans.
Label-Efficient Hyperspectral Image Classification via Spectral FiLM Modulation of Low-Level Pretrained Diffusion Features
CV and Pattern Recognition
Lets computers see details in satellite pictures.