computational imaging

New research presented via EurekAlert describes how artificial intelligence paired with physics-based methods is advancing imaging techniques, including work that makes the invisible visible and automates the colorization of anime footage. The announcement highlights computational imaging as a growing field where machine learning and physical modeling intersect, with potential applications in science and animation production.

A new report highlights that microcontrollers, typically limited to simple embedded tasks, can now run both a diffusion model for image generation and a large language model with 289 million parameters. The development points to AI capabilities moving onto low-cost, low-power hardware rather than requiring cloud servers or GPUs, a notable shift for embedded and edge computing.