Optical Diffusion Models for Image Generation
This addresses efficiency issues in image generation for applications requiring low-power, real-time processing, representing a novel paradigm shift rather than an incremental improvement.
The paper tackles the latency and energy consumption of diffusion models for image generation by implementing them using optical propagation through programmed semi-transparent media, achieving high-speed generation with minimal power consumption.
Diffusion models generate new samples by progressively decreasing the noise from the initially provided random distribution. This inference procedure generally utilizes a trained neural network numerous times to obtain the final output, creating significant latency and energy consumption on digital electronic hardware such as GPUs. In this study, we demonstrate that the propagation of a light beam through a semi-transparent medium can be programmed to implement a denoising diffusion model on image samples. This framework projects noisy image patterns through passive diffractive optical layers, which collectively only transmit the predicted noise term in the image. The optical transparent layers, which are trained with an online training approach, backpropagating the error to the analytical model of the system, are passive and kept the same across different steps of denoising. Hence this method enables high-speed image generation with minimal power consumption, benefiting from the bandwidth and energy efficiency of optical information processing.