Non-line-of-sight imaging under white-light illumination using physics-enhanced deep learning

Non-line-of-sight (NLOS) imaging is an emerging computational imaging technique that allows acquiring information about hidden objects from an indirect view. It has garnered significant attention due to its great potential in medical imaging, security, and autonomous driving, among many others. However, most existing NLOS techniques require active coherent illumination and expensive equipment, which prevents their practical application. Here, we present an NLOS imaging method based on speckle correlation under white-light illumination using an ordinary camera. We exploit a physics-enhanced deep learning technique incorporating a speckle correlation-based model and a denoising prior into a deep neural network to reconstruct the object image. Experimental results demonstrate that our method achieves excellent performance in terms of recovered image quality and scalability. This work further paves the way for the practical application of NLOS imaging in scenarios where coherent illumination and expensive equipment are difficult to deploy.