Searcharxiv⌕ Search

arXiv subjects

Yu Yuan

Publications and source records attributed to Yu Yuan.

At least 55 records · Page 3Linked to original sources
arXiv2022

Ghost-free High Dynamic Range Imaging via Hybrid CNN-Transformer and Structure Tensor

Eliminating ghosting artifacts due to moving objects is a challenging problem in high dynamic range (HDR) imaging. In this letter, we present a hybrid model consisting of a convolutional encoder and a Transformer decoder to generate ghost-free HDR images. In the encoder, a context aggregation network and non-local attention block are adopted to optimize multi-scale features and capture both global and local dependencies of multiple low dynamic range (LDR) images. The decoder based on Swin Transformer is utilized to improve the reconstruction capability of the proposed model. Motivated by the phenomenal difference between the presence and absence of artifacts under the field of structure tensor (ST), we integrate the ST information of LDR images as auxiliary inputs of the network and use ST loss to further constrain artifacts. Different from previous approaches, our network is capable of processing an arbitrary number of input LDR images. Qualitative and quantitative experiments demonstrate the effectiveness of the proposed method by comparing it with existing state-of-the-art HDR deghosting models. Codes are available at https://github.com/pandayuanyu/HSTHdr.

cs.CV↗
arXiv2022

Learning to Kindle the Starlight

Capturing highly appreciated star field images is extremely challenging due to light pollution, the requirements of specialized hardware, and the high level of photographic skills needed. Deep learning-based techniques have achieved remarkable results in low-light image enhancement (LLIE) but have not been widely applied to star field image enhancement due to the lack of training data. To address this problem, we construct the first Star Field Image Enhancement Benchmark (SFIEB) that contains 355 real-shot and 854 semi-synthetic star field images, all having the corresponding reference images. Using the presented dataset, we propose the first star field image enhancement approach, namely StarDiffusion, based on conditional denoising diffusion probabilistic models (DDPM). We introduce dynamic stochastic corruptions to the inputs of conditional DDPM to improve the performance and generalization of the network on our small-scale dataset. Experiments show promising results of our method, which outperforms state-of-the-art low-light image enhancement algorithms. The dataset and codes will be open-sourced.

cs.CV↗
arXiv2022

Internet Of Rights(IOR) In Role Based Block Chain

A large amount of data has been accumulated. with the development of the Internet industry. Many problems have been exposed with data explosion: 1. The contradiction between data privacy and data collaborations; 2. The contradiction between data ownership and the right of data usage; 3. The legality of data collection and data usage; 4. The relationship between the governance of data and the governance of rules; 5. Traceability of evidence chain. In order to face such a complicated situation, many algorithms were proposed and developed. This article tries to build a model from the perspective of blockchain to make some breakthroughs.Internet Of Rights(IOR) model uses multi-chain technology to logically break down the consensus mechanism into layers, including storage consensus, permission consensus, role consensus, transaction consensus etc. thus to build a new infrastructure, which enables data sources with complex organizational structures and interactions to collaborate smoothly on the premise of protecting data privacy. With blockchain's nature of decentralization, openness, autonomy, immutability, and controllable anonymity, Internet Of Rights(IOR) model registers the ownership of data, enables applications to build ecosystem based on responsibilities and rights. It also provides cross-domain processing with privacy protection, as well as the separation of data governance and rule governance. With the processing capabilities of artificial intelligence and big data technology, as well as the ubiquitous data collection capabilities of the Internet of Things, Internet Of Rights(IOR) model may provide a new infrastructure concept for realizing swarm intelligence and building a new paradigm of the Internet, i.e. intelligent governance.

cs.NI↗
arXiv2022

Multimodal Image Fusion based on Hybrid CNN-Transformer and Non-local Cross-modal Attention

The fusion of images taken by heterogeneous sensors helps to enrich the information and improve the quality of imaging. In this article, we present a hybrid model consisting of a convolutional encoder and a Transformer-based decoder to fuse multimodal images. In the encoder, a non-local cross-modal attention block is proposed to capture both local and global dependencies of multiple source images. A branch fusion module is designed to adaptively fuse the features of the two branches. We embed a Transformer module with linear complexity in the decoder to enhance the reconstruction capability of the proposed network. Qualitative and quantitative experiments demonstrate the effectiveness of the proposed method by comparing it with existing state-of-the-art fusion models. The source code of our work is available at https://github.com/pandayuanyu/HCFusion.

cs.CV↗
arXiv2022

Single charge control of localized excitons in heterostructures with ferroelectric thin films and two-dimensional transition metal dichalcogenides

Single charge control of localized excitons (LXs) in two-dimensional transition metal dichalcogenides (TMDCs) is crucial for potential applications in quantum information processing and storage. However, traditional electrostatic doping method with applying metallic gates onto TMDCs may cause the inhomogeneous charge distribution, optical quench, and energy loss. Here, by locally controlling the ferroelectric polarization of the ferroelectric thin film BiFeO3 (BFO) with a scanning probe, we can deterministically manipulate the doping type of monolayer WSe2 to achieve the p-type and n-type doping. This nonvolatile approach can maintain the doping type and hold the localized excitonic charges for a long time without applied voltage. Our work demonstrated that ferroelectric polarization of BFO can control the charges of LXs effectively. Neutral and charged LXs have been observed in different ferroelectric polarization regions, confirmed by magnetic optical measurement. Highly circular polarization degree about 90 % of the photon emission from these quantum emitters have been achieved in high magnetic fields. Controlling single charge of LXs in a non-volatile way shows a great potential for deterministic photon emission with desired charge states for photonic long-term memory.

cond-mat.mes-hall↗
arXiv2021

Topological cavity based on slow light topological edge mode for broadband Purcell enhancement

Slow light in topological valley photonic crystal structures offers new possibilities to enhance light-matter interaction. We report a topological cavity based on slow light topological edge mode for broadband Purcell enhancement. The topological edge modes with large group indices over 100 can be realized with a bearded interface between two topologically distinct valley photonic crystals, featuring the greatly enhanced Purcell factor because of the increased local density of states. In the slow light regime, the topological cavity supports much more cavity modes with higher quality factor than that in the fast light regime, which is both demonstrated theoretically and experimentally. We demonstrate the cavity enables the broadband Purcell enhancement together with substantial Purcell factor, benefiting from dense cavity modes with high quality factor in a wide spectral range. It has great benefit to the realization of high-efficiency quantum-dot-based single-photon sources and entangled-photon sources with less restriction on spectral match. Such topological cavity could serve as a significant building block toward the development of photonic integrated circuits with embedded quantum emitters.

physics.optics↗
arXiv2021

Strong Triplet-Exciton-LO-Phonon Coupling in Two-Dimensional Layered Organic-Inorganic Hybrid Perovskite Single Crystal Microflakes

Two-dimensional (2D) layered hybrid perovskites provide an ideal platform for studying the properties of excitons. Here, we report on a strong triplet-exciton and longitudinal-optical (LO) phonon coupling in 2D (C6H5CH2CH2NH3, PEA)2PbBr4 perovskites. The triplet excitons exhibit strong photoluminescence (PL) in thick perovskite microflakes, and the PL is not detectable for monolayer microflakes. The coupling strength of the triplet exciton-LO phonon is approximately two to three times greater than that of the singlet exciton-LO phonon with a LO phonon energy of about 21 meV. This difference might due to the different locations of singlet excitons located in the well and triplet excitons located in the barrier in the 2D layered perovskite. Revealing the strong coupling of triplet exciton-LO phonon provides a fundamental understanding of many-body interaction in hybrid perovskites, which is useful to develop and optimize the optoelectronic devices based on 2D perovskites in the future.

cond-mat.mes-hall↗
arXiv2020

Sentence Level Human Translation Quality Estimation with Attention-based Neural Networks

This paper explores the use of Deep Learning methods for automatic estimation of quality of human translations. Automatic estimation can provide useful feedback for translation teaching, examination and quality control. Conventional methods for solving this task rely on manually engineered features and external knowledge. This paper presents an end-to-end neural model without feature engineering, incorporating a cross attention mechanism to detect which parts in sentence pairs are most relevant for assessing quality. Another contribution concerns of prediction of fine-grained scores for measuring different aspects of translation quality. Empirical results on a large human annotated dataset show that the neural model outperforms feature-based methods significantly. The dataset and the tools are available.

cs.CL↗
arXiv2019

Hessian estimate for semiconvex solutions to the sigma-2 equation

We derive a priori interior Hessian estimates for semiconvex solutions to the sigma-2 equation. An elusive Jacobi inequality, a transformation rule under the Legendre-Lewy transform, and a mean value inequality for the still nonuniformly elliptic equation without area structure are the key to our arguments. Previously, this result was known for almost convex solutions.

math.AP↗
arXiv2019

Feature-Less End-to-End Nested Term Extraction

In this paper, we proposed a deep learning-based end-to-end method on the domain specified automatic term extraction (ATE), it considers possible term spans within a fixed length in the sentence and predicts them whether they can be conceptual terms. In comparison with current ATE methods, the model supports nested term extraction and does not crucially need extra (extracted) features. Results show that it can achieve high recall and a comparable precision on term extraction task with inputting segmented raw text.

cs.CL↗
arXiv2019

Maximal hypersurfaces over exterior domains

In this paper, we study the exterior problem for the maximal surface equation. We obtain the precise asymptotic behavior of the exterior solution at infinity. And we prove that the exterior Dirichlet problem is uniquely solvable given admissible boundary data and prescribed asymptotic behavior at infinity.

math.AP↗
arXiv2018

All Reality: Virtual, Augmented, Mixed (X), Mediated (X,Y), and Multimediated Reality

The contributions of this paper are: (1) a taxonomy of the "Realities" (Virtual, Augmented, Mixed, Mediated, etc.), and (2) some new kinds of "reality" that come from nature itself, i.e. that expand our notion beyond synthetic realities to include also phenomenological realities. VR (Virtual Reality) replaces the real world with a simulated experience (virtual world). AR (Augmented Reality) allows a virtual world to be experienced while also experiencing the real world at the same time. Mixed Reality provides blends that interpolate between real and virtual worlds in various proportions, along a "Virtuality" axis, and extrapolate to an "X-axis". Mediated Reality goes a step further by mixing/blending and also modifying reality. This modifying of reality introduces a second axis. Mediated Reality is useful as a seeing aid (e.g. modifying reality to make it easier to understand), and for psychology experiments like Stratton's 1896 upside-down eyeglasses experiment. We propose Multimediated Reality as a multidimensional multisensory mediated reality that includes not just interactive multimedia-based reality for our five senses, but also includes additional senses (like sensory sonar, sensory radar, etc.), as well as our human actions/actuators. These extra senses are mapped to our human senses using synthetic synesthesia. This allows us to directly experience real (but otherwise invisible) phenomena, such as wave propagation and wave interference patterns, so that we can see radio waves and sound waves and how they interact with objects and each other. Multimediated reality is multidimensional, multimodal, multisensory, and multiscale. It is also multidisciplinary, in that we must consider not just the user, but also how the technology affects others, e.g. how its physical appearance affects social situations.

cs.HC↗
arXiv2017

A Bernstein problem for special Lagrangian equations in exterior domains

We establish quadratic asymptotics for solutions to special Lagrangian equations with supercritical phases in exterior domains. The method is based on an exterior Liouville type result for general fully nonlinear elliptic equations toward constant asymptotics of bounded Hessian, and also certain rotation arguments toward Hessian bound. Our unified approach also leads to quadratic asymptotics for convex solutions to Monge-Ampère equations (previously known), quadratic Hessian equations, and inverse harmonic Hessian equations over exterior domains.

math.AP↗
arXiv2017

Hamiltonian stationary cones with isotropic links

We show that any closed oriented immersed Hamiltonian stationary isotropic surface $Σ$ with genus $g_Σ$ in $S^{5}\subset\mathbb{C}^{3}$ is (1) Legendrian and minimal if $g_Σ=0$; (2) either Legendrian or with exactly $2g_Σ-2$ Legendrian points if $g_Σ\geq1.$ In general, every compact oriented immersed isotropic submanifold $L^{n-1}\subset S^{2n-1}\subset\mathbb{C}^{n}$ such that the cone $C\left( L^{n-1}\right) $ is Hamiltonian stationary must be Legendrian and minimal if its first Betti number is zero. Corresponding results for non-orientable links are also provided.

math.DG↗