Grayscale to Hyperspectral at Any Resolution Using a Phase-Only Lens
This work enables compact and light-efficient high-resolution snapshot hyperspectral imagers, addressing a domain-specific need in imaging technology.
The paper tackles the ill-posed problem of reconstructing hyperspectral images from grayscale snapshots using a single diffractive optic and filterless sensor, achieving high-quality results with patch sizes as small as the point spread function and providing per-pixel uncertainty estimates that correlate with reconstruction error.
We consider the problem of reconstructing a HxWx31 hyperspectral image from a HxW grayscale snapshot measurement that is captured using only a single diffractive optic and a filterless panchromatic photosensor. This problem is severely ill-posed, but we present the first model that produces high-quality results. We make efficient use of limited data by training a conditional denoising diffusion model that operates on small patches in a shift-invariant manner. During inference, we synchronize per-patch hyperspectral predictions using guidance derived from the optical point spread function. Surprisingly, our experiments reveal that patch sizes as small as the PSFs support achieve excellent results, and they show that local optical cues are sufficient to capture full spectral information. Moreover, by drawing multiple samples, our model provides per-pixel uncertainty estimates that strongly correlate with reconstruction error. Our work lays the foundation for a new class of high-resolution snapshot hyperspectral imagers that are compact and light-efficient.