arXiv subjects

Shi Guo

Publications and source records attributed to Shi Guo.

27 records · Page 2Linked to original sources

arXiv2022

A Differentiable Two-stage Alignment Scheme for Burst Image Reconstruction with Large Shift

Denoising and demosaicking are two essential steps to reconstruct a clean full-color image from the raw data. Recently, joint denoising and demosaicking (JDD) for burst images, namely JDD-B, has attracted much attention by using multiple raw images captured in a short time to reconstruct a single high-quality image. One key challenge of JDD-B lies in the robust alignment of image frames. State-of-the-art alignment methods in feature domain cannot effectively utilize the temporal information of burst images, where large shifts commonly exist due to camera and object motion. In addition, the higher resolution (e.g., 4K) of modern imaging devices results in larger displacement between frames. To address these challenges, we design a differentiable two-stage alignment scheme sequentially in patch and pixel level for effective JDD-B. The input burst images are firstly aligned in the patch level by using a differentiable progressive block matching method, which can estimate the offset between distant frames with small computational cost. Then we perform implicit pixel-wise alignment in full-resolution feature domain to refine the alignment results. The two stages are jointly trained in an end-to-end manner. Extensive experiments demonstrate the significant improvement of our method over existing JDD-B methods. Codes are available at https://github.com/GuoShi28/2StageAlign.

cs.CV↗

arXiv2022

Efficient Long-Range Attention Network for Image Super-resolution

Recently, transformer-based methods have demonstrated impressive results in various vision tasks, including image super-resolution (SR), by exploiting the self-attention (SA) for feature extraction. However, the computation of SA in most existing transformer based models is very expensive, while some employed operations may be redundant for the SR task. This limits the range of SA computation and consequently the SR performance. In this work, we propose an efficient long-range attention network (ELAN) for image SR. Specifically, we first employ shift convolution (shift-conv) to effectively extract the image local structural information while maintaining the same level of complexity as 1x1 convolution, then propose a group-wise multi-scale self-attention (GMSA) module, which calculates SA on non-overlapped groups of features using different window sizes to exploit the long-range image dependency. A highly efficient long-range attention block (ELAB) is then built by simply cascading two shift-conv with a GMSA module, which is further accelerated by using a shared attention mechanism. Without bells and whistles, our ELAN follows a fairly simple design by sequentially cascading the ELABs. Extensive experiments demonstrate that ELAN obtains even better results against the transformer-based SR models but with significantly less complexity. The source code can be found at https://github.com/xindongzhang/ELAN.

cs.CV↗

arXiv2021

Excited State Spectroscopy of Boron Vacancy Defects in Hexagonal Boron Nitride using Time-Resolved Optically Detected Magnetic Resonance

We report optically detected magnetic resonance (ODMR) measurements of an ensemble of spin-1 negatively charged boron vacancies in hexagonal boron nitride. The photoluminescence decay rates are spin-dependent, with inter-system crossing rates of $1.02~\mathrm{ns^{-1}}$ and $2.03~\mathrm{ns^{-1}}$ for the $m_s=0$ and $m_s=\pm 1$ states, respectively. Time-gating the photoluminescence enhances the ODMR contrast by discriminating between different decay rates. This is particularly effective for detecting the spin of the optically excited state, where a zero-field splitting of $\vert D_{ES}\vert=2.09~\mathrm{GHz}$ is measured. The magnetic field dependence of the time-gated photoluminescence exhibits dips corresponding to the Ground (GSLAC) and excited-state (ESLAC) anti-crossings. Additional dips corresponding to anti-crossings with nearby spin-1/2 parasitic impurities are also observed. The ESLAC dip is sensitive to the angle of the external magnetic field. Comparison to a model suggests that the anti-crossings are mediated by the interaction with nuclear spins, and allow an estimate of the ratio of the spin-dependent relaxation rates from the singlet back into the triplet ground state of $κ_0/κ_1=0.34$. This work provides important spectroscopic signatures of the boron vacancy, and information on the spin pumping and read-out dynamics.

cond-mat.mtrl-sci↗

arXiv2021

HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset

High dynamic range (HDR) video reconstruction from sequences captured with alternating exposures is a very challenging problem. Existing methods often align low dynamic range (LDR) input sequence in the image space using optical flow, and then merge the aligned images to produce HDR output. However, accurate alignment and fusion in the image space are difficult due to the missing details in the over-exposed regions and noise in the under-exposed regions, resulting in unpleasing ghosting artifacts. To enable more accurate alignment and HDR fusion, we introduce a coarse-to-fine deep learning framework for HDR video reconstruction. Firstly, we perform coarse alignment and pixel blending in the image space to estimate the coarse HDR video. Secondly, we conduct more sophisticated alignment and temporal fusion in the feature space of the coarse HDR video to produce better reconstruction. Considering the fact that there is no publicly available dataset for quantitative and comprehensive evaluation of HDR video reconstruction methods, we collect such a benchmark dataset, which contains $97$ sequences of static scenes and 184 testing pairs of dynamic scenes. Extensive experiments show that our method outperforms previous state-of-the-art methods. Our dataset, code and model will be made publicly available.

cs.CV↗

arXiv2021

Text Prior Guided Scene Text Image Super-resolution

Scene text image super-resolution (STISR) aims to improve the resolution and visual quality of low-resolution (LR) scene text images, and consequently boost the performance of text recognition. However, most of existing STISR methods regard text images as natural scene images, ignoring the categorical information of text. In this paper, we make an inspiring attempt to embed categorical text prior into STISR model training. Specifically, we adopt the character probability sequence as the text prior, which can be obtained conveniently from a text recognition model. The text prior provides categorical guidance to recover high-resolution (HR) text images. On the other hand, the reconstructed HR image can refine the text prior in return. Finally, we present a multi-stage text prior guided super-resolution (TPGSR) framework for STISR. Our experiments on the benchmark TextZoom dataset show that TPGSR can not only effectively improve the visual quality of scene text images, but also significantly improve the text recognition accuracy over existing STISR methods. Our model trained on TextZoom also demonstrates certain generalization capability to the LR images in other datasets.

cs.CV↗

arXiv2021

Joint Denoising and Demosaicking with Green Channel Prior for Real-world Burst Images

Denoising and demosaicking are essential yet correlated steps to reconstruct a full color image from the raw color filter array (CFA) data. By learning a deep convolutional neural network (CNN), significant progress has been achieved to perform denoising and demosaicking jointly. However, most existing CNN-based joint denoising and demosaicking (JDD) methods work on a single image while assuming additive white Gaussian noise, which limits their performance on real-world applications. In this work, we study the JDD problem for real-world burst images, namely JDD-B. Considering the fact that the green channel has twice the sampling rate and better quality than the red and blue channels in CFA raw data, we propose to use this green channel prior (GCP) to build a GCP-Net for the JDD-B task. In GCP-Net, the GCP features extracted from green channels are utilized to guide the feature extraction and feature upsampling of the whole image. To compensate for the shift between frames, the offset is also estimated from GCP features to reduce the impact of noise. Our GCP-Net can preserve more image structures and details than other JDD methods while removing noise. Experiments on synthetic and real-world noisy images demonstrate the effectiveness of GCP-Net quantitatively and qualitatively.

eess.IV↗

arXiv2019

Toward Convolutional Blind Denoising of Real Photographs

While deep convolutional neural networks (CNNs) have achieved impressive success in image denoising with additive white Gaussian noise (AWGN), their performance remains limited on real-world noisy photographs. The main reason is that their learned models are easy to overfit on the simplified AWGN model which deviates severely from the complicated real-world noise model. In order to improve the generalization ability of deep CNN denoisers, we suggest training a convolutional blind denoising network (CBDNet) with more realistic noise model and real-world noisy-clean image pairs. On the one hand, both signal-dependent noise and in-camera signal processing pipeline is considered to synthesize realistic noisy images. On the other hand, real-world noisy photographs and their nearly noise-free counterparts are also included to train our CBDNet. To further provide an interactive strategy to rectify denoising result conveniently, a noise estimation subnetwork with asymmetric learning to suppress under-estimation of noise level is embedded into CBDNet. Extensive experimental results on three datasets of real-world noisy photographs clearly demonstrate the superior performance of CBDNet over state-of-the-arts in terms of quantitative metrics and visual quality. The code has been made available at https://github.com/GuoShi28/CBDNet.

cs.CV↗

arXiv2016

Spin-Orbit Interactions in Electronic Structure Quantum Monte Carlo

We develop generalization of the fixed-phase diffusion Monte Carlo method for Hamiltonians which explicitly depend on particle spins such as for spin-orbit interactions. The method is formulated in zero variance manner and is similar to treatment of nonlocal operators in commonly used static- spin calculations. Tests on atomic and molecular systems show that it is very accurate, on par with the fixed-node method. This opens electronic structure quantum Monte Carlo methods to a vast research area of quantum phenomena in which spin-related interactions play an important role.

cond-mat.str-el↗

arXiv2013

Study of dipole moments of LiSr and KRb molecules by quantum Monte Carlo methods

Heteronuclear dimers are of significant interest to experiments seeking to exploit ultracold polar molecules in a number of novel ways including precision measurement, quantum computing, and quantum simulation. We calculate highly accurate Born-Oppenheimer total energies and electric dipole moments as a function of internuclear separation for two such dimers, LiSr and KRb. We apply fully-correlated, high-accuracy quantum Monte Carlo methods for evaluating these molecular properties in a many-body framework. We use small-core effective potentials combined with multi-reference Slater-Jastrow trial wave functions to provide accurate nodes for the fixed-node diffusion Monte Carlo method. For reference and comparison, we calculate the same properties with Hartree-Fock and with restricted Configuration Interaction methods, and carefully assess the impact of the recovered many-body correlations on the calculated quantities. For LiSr we find a highly nonlinear dipole moment curve, which may make this molecule's dipole moment tunable through vibrational state control.

quant-ph↗