Related papers: Nonlinear wavefront reconstruction from a pyramid …
Deep convolutional neural networks (CNN) brought revolution without any doubt to various challenging tasks, mainly in computer vision. However, their model designing still requires attention to reduce number of learnable parameters, with no…
Surface reconstruction has traditionally relied on the Multi-View Stereo (MVS)-based pipeline, which often suffers from noisy and incomplete geometry. This is due to that although MVS has been proven to be an effective way to recover the…
Exoplanet direct imaging using adaptive optics (AO) is often limited by non-common path aberrations (NCPAs) and aberrations that are invisible to traditional pupil-plane wavefront sensors (WFSs). This can be remedied by focal-plane (FP)…
Adaptive optics (AO) is a technique allowing to drastically improve ground-based telescopes angular resolution. The wavefront sensor (WFS) is one of the key components of such systems, driving the fundamental performance limitations. In…
The nonlinear curvature wavefront sensor (nlCWFS) offers improved sensitivity for adaptive optics (AO) systems compared to existing wavefront sensors, such as the Shack-Hartmann. The nominal nlCWFS design uses a series of imaging planes…
Ultra-thin multimode optical fiber imaging promises next-generation medical endoscopes reaching high image resolution for deep tissues. However, current technology suffers from severe optical distortion, as the fiber's calibration is…
Non-invasive subsurface imaging using full waveform inversion (FWI) has the potential to fundamentally change engineering site characterization by enabling the recovery of high resolution 2D/3D maps of subsurface stiffness. Yet, the…
During the last years, Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in image classification. Their architectures have largely drawn inspiration by models of the primate visual system. However, while recent…
The Zernike wavefront sensor (ZWFS) stands out as one of the most sensitive optical systems for measuring the phase of an incoming wavefront, reaching photon efficiencies close to the fundamental limit. This quality, combined with the fact…
Full-waveform inversion (FWI) is an accurate imaging approach for modeling velocity structure by minimizing the misfit between recorded and predicted seismic waveforms. However, the strong non-linearity of FWI resulting from fitting…
This study presents a hybrid deep learning framework, the Vision Transformer with Residual Feature Network (VRF-Net), for recovering high-resolution system matrices in Magnetic Particle Imaging (MPI). MPI resolution often suffers from…
The tradeoff between receptive field size and efficiency is a crucial issue in low level vision. Plain convolutional networks (CNNs) generally enlarge the receptive field at the expense of computational cost. Recently, dilated filtering has…
The high sensitivity of the pyramid wavefront sensor has made it the preferred sensor in high contrast adaptive optics systems. Future higher contrast systems, like the Extremely Large Telescope's Planetary Camera System, will require…
Photonic crystal waveguides (PCWs) play a critical role in precisely controlling light propagation, enabling high-performance functions in applications such as optical communication and integrated photonics. The design of PCWs traditionally…
The MMTO Adaptive optics exoPlanet characterization System (MAPS) is an ongoing upgrade to the 6.5-meter MMT Observatory on Mount Hopkins in Arizona. MAPS includes an upgraded adaptive secondary mirror (ASM), upgrades to the ARIES…
Neural networks allow solving many ill-posed inverse problems with unprecedented performance. Physics informed approaches already progressively replace carefully hand-crafted reconstruction algorithms in real applications. However, these…
Multi-user multiple-input multiple-output (MU-MIMO) beamforming design is typically formulated as a non-convex weighted sum rate (WSR) maximization problem that is known to be NP-hard. This problem is solved either by iterative algorithms,…
In computer vision, convolutional networks (CNNs) often adopts pooling to enlarge receptive field which has the advantage of low computational complexity. However, pooling can cause information loss and thus is detrimental to further…
This work investigates use of equivariant neural networks as efficient and high-performance frameworks for image reconstruction and denoising in nuclear medicine. Our work aims to tackle limitations of conventional Convolutional Neural…
We investigate neural network image reconstruction for magnetic particle imaging. The network performance depends strongly on the convolution effects of the spectrum input data. The larger convolution effect appearing at a relatively…