Hi-SPAD: Video-Rate Hyperspectral Imaging and Inference with Single-Photon Cameras

We present Hi-SPAD, a hyperspectral imaging system that combines a pushbroom architecture with single-photon avalanche diode (SPAD) sensors to enable high spatial, spectral and temporal resolutions under passive ambient light. While SPAD-based spectral sensing and the pushbroom configuration have been explored separately, our key contribution lies in combining these technologies while addressing SPAD-specific challenges. We provide a theoretical analysis showing that, despite the heavily quantized and nonlinear nature of SPAD measurements, accurate material classification and full-spectrum reconstruction can be achieved with exponentially decreasing error bounds as the number of measurements increases. These results are validated through simulations and real data from our lab prototype, establishing the feasibility of photon-counting hyperspectral video in dynamic scenes. Additionally, we evaluate reconstruction methods for Hi-SPAD that support robust imaging under passive ambient illumination. Our lab-built Hi-SPAD camera enables hyperspectral video at 26 frames per second with 123 spectral channels, even under ambient lighting.