Search arXivSearch

arXiv · 2407.10897

Optical Diffusion Models for Image Generation

Abstract

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.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Ilker Oguz, Niyazi Ulas Dinc, Mustafa Yildirim, Junjie Ke, Innfarn Yoo, Qifei Wang, Feng Yang, Christophe Moser, Demetri Psaltis. 2024-10-31. Optical Diffusion Models for Image Generation. https://arxiv.org/abs/2407.10897

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

Rubidium referenced Kerr comb with cavity phase matching

Phase matching is a fundamental problem in nonlinear optics that is normally constrained by material dispersion. The limited operation wavelengths within phase matching window limits the application, including the precise metrology using Kerr combs. Demanding applications like compact optical clock and astronomical spectroscopy requires atomic reference around 800 nm, where the natural phase matching is challenging. Here we revisit the concept of cavity phase matching (CPM), and fully reveal its advantage to engineer artificial phase matching beyond material dispersion. With the access of CPM condition in a monolithic high-Q fiber Fabry-Pérot resonator featuring a macroscopic cavity length, we achieve low noise Kerr comb generation around 800 nm, within the power budget of a single-mode laser diode. Inside a pump-integrated package of 19 cm3, low phase noise of -125 dBc/Hz at 100 kHz offset frequency is achieved for a 10.1 GHz repetition rate. Most importantly, the generated Kerr comb has been directly referenced to rubidium atomic transition for long-term stable operation. This result not only opens a new way for Kerr comb generation at arbitrary wavelengths, but also can be generalized to any other nonlinear optical frequency conversion application.

physics.optics

Mid-infrared reconfiguration of population flow in lanthanide nanocrystals

Converting mid-infrared (MIR) radiation to visible or near-infrared wavelengths is essential for imaging and sensing, yet achieving sensitive, low-power, and scalable detection remains challenging. Lanthanide nanocrystals provide an alternative through ratiometric luminescence but are typically constrained by Boltzmann statistics, which tie population distributions to lattice temperature and limit signal contrast. Here we show that MIR irradiation rebalances dissipative relaxation pathways, driving lanthanide emitters into a non-Boltzmann steady state that enables non-thermal control of population distributions. This allows emission behaviors inaccessible under thermal equilibrium. We exploit this regime to achieve linear MIR detection with respect to MIR power across 6.8 to 8.6 micrometers. The ratiometric response is intrinsically independent of the pump power, enabling operation at an ultralow excitation power of 10 uW, several orders of magnitude lower than conventional approaches. Using standard silicon photodetectors, we then demonstrate room-temperature MIR imaging with detection limits approaching 4 nW um-2. Our results establish lanthanide nanoparticles as an efficient platform for MIR conversion and sensing in nanophotonic systems.

physics.optics

Intracavity THz generation using a thin lithium niobate plate in a compact Kerr-lens mode-locked Yb:CALGO bulk oscillator

We demonstrate intracavity terahertz (THz) generation via optical rectification in a 50-m-thick lithium niobate crystal placed inside a compact diode-pumped Kerr-lens mode-locked (KLM) Yb:CALGO bulk oscillator. The oscillator operates at a repetition rate of 85 MHz and delivers 83-fs pulses with up to 71 W of average intracavity power, obtained with only 21.4 W of low-cost multimode diode pump power. We generate single-cycle THz pulses with a spectrum extending up to 3 THz, detected by electro-optic sampling with 60 dB dynamic range within 156 s of measurement time (313 averaged traces) and up to 120 W of THz average power. This work combines the high damage threshold, power-handling capability, and cost-effectiveness of thin LN plates with simplicity, compactness, and low-cost multimode diode-pumped solid-state bulk lasers, offering an attractive alternative for high-repetition-rate THz time-domain spectroscopy systems.

physics.optics