arXiv subjects

Siqi Li

Publications and source records attributed to Siqi Li.

113 records · Page 7Linked to original sources

arXiv2020

Low-Dose CT Image Denoising Using Parallel-Clone Networks

Deep neural networks have a great potential to improve image denoising in low-dose computed tomography (LDCT). Popular ways to increase the network capacity include adding more layers or repeating a modularized clone model in a sequence. In such sequential architectures, the noisy input image and end output image are commonly used only once in the training model, which however limits the overall learning performance. In this paper, we propose a parallel-clone neural network method that utilizes a modularized network model and exploits the benefit of parallel input, parallel-output loss, and clone-toclone feature transfer. The proposed model keeps a similar or less number of unknown network weights as compared to conventional models but can accelerate the learning process significantly. The method was evaluated using the Mayo LDCT dataset and compared with existing deep learning models. The results show that the use of parallel input, parallel-output loss, and clone-to-clone feature transfer all can contribute to an accelerated convergence of deep learning and lead to improved image quality in testing. The parallel-clone network has been demonstrated promising for LDCT image denoising.

eess.IV↗

arXiv2020

Attention-based Multi-modal Fusion Network for Semantic Scene Completion

This paper presents an end-to-end 3D convolutional network named attention-based multi-modal fusion network (AMFNet) for the semantic scene completion (SSC) task of inferring the occupancy and semantic labels of a volumetric 3D scene from single-view RGB-D images. Compared with previous methods which use only the semantic features extracted from RGB-D images, the proposed AMFNet learns to perform effective 3D scene completion and semantic segmentation simultaneously via leveraging the experience of inferring 2D semantic segmentation from RGB-D images as well as the reliable depth cues in spatial dimension. It is achieved by employing a multi-modal fusion architecture boosted from 2D semantic segmentation and a 3D semantic completion network empowered by residual attention blocks. We validate our method on both the synthetic SUNCG-RGBD dataset and the real NYUv2 dataset and the results show that our method respectively achieves the gains of 2.5% and 2.6% on the synthetic SUNCG-RGBD dataset and the real NYUv2 dataset against the state-of-the-art method.

cs.CV↗

arXiv2019

Attosecond Transient Absorption Spooktroscopy: a ghost imaging approach to ultrafast absorption spectroscopy

The recent demonstration of isolated attosecond pulses from an X-ray free-electron laser (XFEL) opens the possibility for probing ultrafast electron dynamics at X-ray wavelengths. An established experimental method for probing ultrafast dynamics is X-ray transient absorption spectroscopy, where the X-ray absorption spectrum is measured by scanning the central photon energy and recording the resultant photoproducts. The spectral bandwidth inherent to attosecond pulses is wide compared to the resonant features typically probed, which generally precludes the application of this technique in the attosecond regime. In this paper we propose and demonstrate a new technique to conduct transient absorption spectroscopy with broad bandwidth attosecond pulses with the aid of ghost imaging, recovering sub-bandwidth resolution in photoproduct-based absorption measurements.

physics.chem-ph↗

arXiv2019

Tunable Isolated Attosecond X-ray Pulses with Gigawatt Peak Power from a Free-Electron Laser

The quantum mechanical motion of electrons in molecules and solids occurs on the sub-femtosecond timescale. Consequently, the study of ultrafast electronic phenomena requires the generation of laser pulses shorter than 1 fs and of sufficient intensity to interact with their target with high probability. Probing these dynamics with atomic-site specificity requires the extension of sub-femtosecond pulses to the soft X-ray spectral region. Here we report the generation of isolated GW-scale soft X-ray attosecond pulses with an X-ray free-electron laser. Our source has a pulse energy that is six orders of magnitude larger than any other source of isolated attosecond pulses in the soft X-ray spectral region, with a peak power in the tens of gigawatts. This unique combination of high intensity, high photon energy and short pulse duration enables the investigation of electron dynamics with X-ray non-linear spectroscopy and single-particle imaging.

physics.optics↗

arXiv2018

Coherent Space-Charge to X-ray Up-Conversion in Gas

We theoretically investigate the use of the intense transverse field created by a relativistic electron bunch to drive strong-field processes. Such bunches can be easily implemented from beam shaping in existing electron accelerators. We focus on the process of strong-field driven high harmonic generation and calculate the single-atom dipole response to the space-charge field of relativistic tilted electron beam. We compare the emitted radiation spectrum of the space-charge field to that of a few-cycle laser pulse and show that the space-charge field creates a spectrum which extends much further into the X-ray domain. We apply simple classical trajectory analysis to understand this result.

physics.acc-ph↗