arXiv subjects

Lei Xiao

Publications and source records attributed to Lei Xiao.

At least 73 records · Page 4Linked to original sources

arXiv2022

View Synthesis of Dynamic Scenes based on Deep 3D Mask Volume

Image view synthesis has seen great success in reconstructing photorealistic visuals, thanks to deep learning and various novel representations. The next key step in immersive virtual experiences is view synthesis of dynamic scenes. However, several challenges exist due to the lack of high-quality training datasets, and the additional time dimension for videos of dynamic scenes. To address this issue, we introduce a multi-view video dataset, captured with a custom 10-camera rig in 120FPS. The dataset contains 96 high-quality scenes showing various visual effects and human interactions in outdoor scenes. We develop a new algorithm, Deep 3D Mask Volume, which enables temporally-stable view extrapolation from binocular videos of dynamic scenes, captured by static cameras. Our algorithm addresses the temporal inconsistency of disocclusions by identifying the error-prone areas with a 3D mask volume, and replaces them with static background observed throughout the video. Our method enables manipulation in 3D space as opposed to simple 2D masks, We demonstrate better temporal stability than frame-by-frame static view synthesis methods, or those that use 2D masks. The resulting view synthesis videos show minimal flickering artifacts and allow for larger translational movements.

cs.CV↗

arXiv2022

NeuralPassthrough: Learned Real-Time View Synthesis for VR

Virtual reality (VR) headsets provide an immersive, stereoscopic visual experience, but at the cost of blocking users from directly observing their physical environment. Passthrough techniques are intended to address this limitation by leveraging outward-facing cameras to reconstruct the images that would otherwise be seen by the user without the headset. This is inherently a real-time view synthesis challenge, since passthrough cameras cannot be physically co-located with the eyes. Existing passthrough techniques suffer from distracting reconstruction artifacts, largely due to the lack of accurate depth information (especially for near-field and disoccluded objects), and also exhibit limited image quality (e.g., being low resolution and monochromatic). In this paper, we propose the first learned passthrough method and assess its performance using a custom VR headset that contains a stereo pair of RGB cameras. Through both simulations and experiments, we demonstrate that our learned passthrough method delivers superior image quality compared to state-of-the-art methods, while meeting strict VR requirements for real-time, perspective-correct stereoscopic view synthesis over a wide field of view for desktop-connected headsets.

cs.CV↗

arXiv2022

SNeRF: Stylized Neural Implicit Representations for 3D Scenes

This paper presents a stylized novel view synthesis method. Applying state-of-the-art stylization methods to novel views frame by frame often causes jittering artifacts due to the lack of cross-view consistency. Therefore, this paper investigates 3D scene stylization that provides a strong inductive bias for consistent novel view synthesis. Specifically, we adopt the emerging neural radiance fields (NeRF) as our choice of 3D scene representation for their capability to render high-quality novel views for a variety of scenes. However, as rendering a novel view from a NeRF requires a large number of samples, training a stylized NeRF requires a large amount of GPU memory that goes beyond an off-the-shelf GPU capacity. We introduce a new training method to address this problem by alternating the NeRF and stylization optimization steps. Such a method enables us to make full use of our hardware memory capacity to both generate images at higher resolution and adopt more expressive image style transfer methods. Our experiments show that our method produces stylized NeRFs for a wide range of content, including indoor, outdoor and dynamic scenes, and synthesizes high-quality novel views with cross-view consistency.

cs.CV↗

arXiv2022

Simulating non-Hermitian quasicrystals with single-photon quantum walks

Non-Hermiticity significantly enriches the properties of topological models, leading to exotic features such as the non-Hermitian skin effects and non-Bloch bulk-boundary correspondence that have no counterparts in Hermitian settings. Its impact is particularly illustrating in non-Hermitian quasicrystals where the interplay between non-Hermiticity and quasiperiodicity results in the concurrence of the delocalization-localization transition, the parity-time (PT)-symmetry breaking, and the onset of the non-Hermitian skin effects. Here we experimentally simulate non-Hermitian quasicrystals using photonic quantum walks. Using dynamic observables, we demonstrate that the system can transit from a delocalized, PT-symmetry broken phase that features non-Hermitian skin effects, to a localized, PT-symmetry unbroken phase with no non-Hermitian skin effects. The measured critical point is consistent with the theoretical prediction through a spectral winding number, confirming the topological origin of the phase transition. Our work opens the avenue of investigating the interplay of non-Hermiticity, quasiperiodicity, and spectral topology in open quantum systems.

cond-mat.mes-hall↗

arXiv2022

Mixture of Virtual-Kernel Experts for Multi-Objective User Profile Modeling

In industrial applications like online advertising and recommendation systems, diverse and accurate user profiles can greatly help improve personalization. Deep learning is widely applied to mine expressive tags to users from their historical interactions in the system, e.g., click, conversion action in the advertising chain. The usual approach is to take a certain action as the objective, and introduce multiple independent Two-Tower models to predict the possibility of users' action on tags (known as CTR or CVR prediction). The predicted users' high probably attractive tags are to represent their preferences. However, the single-action models cannot learn complementarily and support effective training on data-sparse actions. Besides, limited by the lack of information fusion between the two towers, the model learns insufficiently to represent users' preferences on various tag \textbf{topics} well. This paper introduces a novel multi-task model called Mixture of Virtual-Kernel Experts (MVKE) to learn user preferences on various actions and topics unitedly. In MVKE, we propose a concept of Virtual-Kernel Expert, which focuses on modeling one particular facet of the user's preferences, and all of them learn coordinately. Besides, the gate-based structure used in MVKE builds an information fusion bridge between two towers, improving the model's capability and maintaining high efficiency. We apply the model in Tencent Advertising System, where both online and offline evaluations show that our method has a significant improvement compared with the existing ones and brings about an obvious lift to actual advertising revenue.

cs.IR↗

arXiv2022

Synchronous observation of Bell nonlocality and state-dependent Kochen-Specker contextuality

Bell nonlocality and Kochen-Specker contextuality are two remarkable nonclassical features of quantum theory, related to strong correlations between outcomes of measurements performed on quantum systems. Both phenomena can be witnessed by the violation of certain inequalities, the simplest and most important of which are the Clauser-Horne-Shimony-Holt (CHSH) and the Klyachko-Can-Binicioǧlu-Shumovski (KCBS), for Bell nonlocality and Kochen-Specker contextuality, respectively. It has been shown that, using the most common interpretation of Bell scenarios, quantum systems cannot violate both inequalities concomitantly, thus suggesting a monogamous relation between the two phenomena. In this Letter, we show that the joint consideration of the CHSH and KCBS inequalities naturally calls for the so-called generalized Bell scenarios, which, contrary to the previous results, allows for joint violation of them. A photonic experiment thus tests the synchronous violation of both CHSH and KCBS inequalities. Our results agree with the theoretical predictions, thereby providing experimental proof of the coexistence of Bell nonlocality and Kochen-Specker contextuality in the simplest scenario, and shed new light for further explorations of nonclassical features of quantum systems.

quant-ph↗

arXiv2022

Experimental realization of a quantum image classifier via tensor-network-based machine learning

Quantum machine learning aspires to overcome intractability that currently limits its applicability to practical problems. However, quantum machine learning itself is limited by low effective dimensions achievable in state-of-the-art experiments. Here we demonstrate highly successful classifications of real-life images using photonic qubits, combining a quantum tensor-network representation of hand-written digits and entanglement-based optimization. Specifically, we focus on binary classification for hand-written zeroes and ones, whose features are cast into the tensor-network representation, further reduced by optimization based on entanglement entropy and encoded into two-qubit photonic states. We then demonstrate image classification with a high success rate exceeding 98%, through successive gate operations and projective measurements. Although we work with photons, our approach is amenable to other physical realizations such as nitrogen-vacancy centers, nuclear spins and trapped ions, and our scheme can be scaled to efficient multi-qubit encodings of features in the tensor-product representation, thereby setting the stage for quantum-enhanced multi-class classification.

quant-ph↗

arXiv2021

Follow the Prophet: Accurate Online Conversion Rate Prediction in the Face of Delayed Feedback

The delayed feedback problem is one of the imperative challenges in online advertising, which is caused by the highly diversified feedback delay of a conversion varying from a few minutes to several days. It is hard to design an appropriate online learning system under these non-identical delay for different types of ads and users. In this paper, we propose to tackle the delayed feedback problem in online advertising by "Following the Prophet" (FTP for short). The key insight is that, if the feedback came instantly for all the logged samples, we could get a model without delayed feedback, namely the "prophet". Although the prophet cannot be obtained during online learning, we show that we could predict the prophet's predictions by an aggregation policy on top of a set of multi-task predictions, where each task captures the feedback patterns of different periods. We propose the objective and optimization approach for the policy, and use the logged data to imitate the prophet. Extensive experiments on three real-world advertising datasets show that our method outperforms the previous state-of-the-art baselines.

cs.LG↗

arXiv2021

Observation of non-Hermitian topological Anderson insulator in quantum dynamics

Disorder and non-Hermiticity dramatically impact the topological and localization properties of a quantum system, giving rise to intriguing quantum states of matter. The rich interplay of disorder, non-Hermiticity, and topology is epitomized by the recently proposed non-Hermitian topological Anderson insulator that hosts a plethora of exotic phenomena. Here we experimentally simulate the non-Hermitian topological Anderson insulator using disordered photonic quantum walks, and characterize its localization and topological properties. In particular, we focus on the competition between Anderson localization induced by random disorder, and the non-Hermitian skin effect under which all eigenstates are squeezed toward the boundary. The two distinct localization mechanisms prompt a non-monotonous change in profile of the Lyapunov exponent, which we experimentally reveal through dynamic observables. We then probe the disorder-induced topological phase transitions, and demonstrate their biorthogonal criticality. Our experiment further advances the frontier of synthetic topology in open systems.

cond-mat.mes-hall↗

arXiv2021

Detecting non-Bloch topological invariants in quantum dynamics

Non-Bloch topological invariants preserve the bulk-boundary correspondence in non-Hermitian topological systems, and are a key concept in the contemporary study of non-Hermitian topology. Here we report the dynamic detection of non-Bloch topological invariants in single-photon quantum walks, revealed through the biorthogonal chiral displacement, and crosschecked with the dynamic spin textures in the generalized quasimomentum-time domain following a quantum quench. Both detection schemes are robust against symmetry-preserving disorders, and yield consistent results with theoretical predictions. Our experiments are performed far away from any boundaries, and therefore underline non-Bloch topological invariants as intrinsic properties of the system that persist in the thermodynamic limit. Our work sheds new light on the experimental investigation of non-Hermitian topology.

cond-mat.mes-hall↗

arXiv2021

Simulating Exceptional Non-Hermitian Metals with Single-Photon Interferometry

We experimentally simulate in a photonic setting non-Hermitian (NH) metals characterized by the topological properties of their nodal band structures. Implementing nonunitary time evolution in reciprocal space followed by interferometric measurements, we probe the complex eigenenergies of the corresponding NH Bloch Hamiltonians, and study in detail the topology of their exceptional lines (ELs), the NH counterpart of nodal lines in Hermitian systems. We focus on two distinct types of NH metals: two-dimensional systems with symmetry-protected ELs, and three-dimensional systems possessing symmetry-independent topological ELs in the form of knots. While both types feature open Fermi surfaces, we experimentally observe their distinctions by analyzing the impact of symmetry-breaking perturbations on the topology of ELs.

quant-ph↗

arXiv2021

LiveView: Dynamic Target-Centered MPI for View Synthesis

Existing Multi-Plane Image (MPI) based view-synthesis methods generate an MPI aligned with the input view using a fixed number of planes in one forward pass. These methods produce fast, high-quality rendering of novel views, but rely on slow and computationally expensive MPI generation methods unsuitable for real-time applications. In addition, most MPI techniques use fixed depth/disparity planes which cannot be modified once the training is complete, hence offering very little flexibility at run-time. We propose LiveView - a novel MPI generation and rendering technique that produces high-quality view synthesis in real-time. Our method can also offer the flexibility to select scene-dependent MPI planes (number of planes and spacing between them) at run-time. LiveView first warps input images to target view (target-centered) and then learns to generate a target view centered MPI, one depth plane at a time (dynamically). The method generates high-quality renderings, while also enabling fast MPI generation and novel view synthesis. As a result, LiveView enables real-time view synthesis applications where an MPI needs to be updated frequently based on a video stream of input views. We demonstrate that LiveView improves the quality of view synthesis while being 70 times faster at run-time compared to state-of-the-art MPI-based methods.

cs.CV↗

arXiv2021

Observation of non-Bloch parity-time symmetry and exceptional points

Parity-time (PT)-symmetric Hamiltonians have widespread significance in non-Hermitian physics. A PT-symmetric Hamiltonian can exhibit distinct phases with either real or complex eigenspectrum, while the transition points in between, the so-called exceptional points, give rise to a host of critical behaviors that holds great promise for applications. For spatially periodic non-Hermitian systems, PT symmetries are commonly characterized and observed in line with the Bloch band theory, with exceptional points dwelling in the Brillouin zone. Here, in nonunitary quantum walks of single photons, we uncover a novel family of exceptional points beyond this common wisdom. These "non-Bloch exceptional points" originate from the accumulation of bulk eigenstates near boundaries, known as the non-Hermitian skin effect, and inhabit a generalized Brillouin zone. Our finding opens the avenue toward a generalized PT-symmetry framework, and reveals the intriguing interplay between PT symmetry and non-Hermitian skin effect.

quant-ph↗

arXiv2021

Quantum information dynamics in a high-dimensional parity-time-symmetric system

Non-Hermitian systems with parity-time ($\mathcal{PT}$) symmetry give rise to exceptional points (EPs) with exceptional properties that arise due to the coalescence of eigenvectors. Such systems have been extensively explored in the classical domain, where second or higher order EPs have been proposed or realized. In contrast, quantum information studies of $\mathcal{PT}$-symmetric systems have been confined to systems with a two-dimensional Hilbert space. Here by using a single-photon interferometry setup, we simulate quantum dynamics of a four-dimensional $\mathcal{PT}$-symmetric system across a fourth-order exceptional point. By tracking the coherent, non-unitary evolution of the density matrix of the system in $\mathcal{PT}$-symmetry unbroken and broken regions, we observe the entropy dynamics for both the entire system, and the gain and loss subsystems. Our setup is scalable to the higher-dimensional $\mathcal{PT}$-symmetric systems, and our results point towards the rich dynamics and critical properties.

quant-ph↗

arXiv2020

RUArt: A Novel Text-Centered Solution for Text-Based Visual Question Answering

Text-based visual question answering (VQA) requires to read and understand text in an image to correctly answer a given question. However, most current methods simply add optical character recognition (OCR) tokens extracted from the image into the VQA model without considering contextual information of OCR tokens and mining the relationships between OCR tokens and scene objects. In this paper, we propose a novel text-centered method called RUArt (Reading, Understanding and Answering the Related Text) for text-based VQA. Taking an image and a question as input, RUArt first reads the image and obtains text and scene objects. Then, it understands the question, OCRed text and objects in the context of the scene, and further mines the relationships among them. Finally, it answers the related text for the given question through text semantic matching and reasoning. We evaluate our RUArt on two text-based VQA benchmarks (ST-VQA and TextVQA) and conduct extensive ablation studies for exploring the reasons behind RUArt's effectiveness. Experimental results demonstrate that our method can effectively explore the contextual information of the text and mine the stable relationships between the text and objects.

cs.CV↗

arXiv2020

KCoreMotif: An Efficient Graph Clustering Algorithm for Large Networks by Exploiting k-core Decomposition and Motifs

Clustering analysis has been widely used in trust evaluation on various complex networks such as wireless sensors networks and online social networks. Spectral clustering is one of the most commonly used algorithms for graph-structured data (networks). However, the conventional spectral clustering is inherently difficult to work with large-scale networks due to the fact that it needs computationally expensive matrix manipulations. To deal with large networks, in this paper, we propose an efficient graph clustering algorithm, KCoreMotif, specifically for large networks by exploiting k-core decomposition and motifs. The essential idea behind the proposed clustering algorithm is to perform the efficient motif-based spectral clustering algorithm on k-core subgraphs, rather than on the entire graph. More specifically, (1) we first conduct the k-core decomposition of the large input network; (2) we then perform the motif-based spectral clustering for the top k-core subgraphs; (3) we group the remaining vertices in the rest (k-1)-core subgraphs into previously found clusters; and finally obtain the desired clusters of the large input network. To evaluate the performance of the proposed graph clustering algorithm KCoreMotif, we use both the conventional and the motif-based spectral clustering algorithms as the baselines and compare our algorithm with them for 18 groups of real-world datasets. Comparative results demonstrate that the proposed graph clustering algorithm is accurate yet efficient for large networks, which also means that it can be further used to evaluate the intra-cluster and inter-cluster trusts on large networks.

cs.SI↗

arXiv2020

A feature-supervised generative adversarial network for environmental monitoring during hazy days

The adverse haze weather condition has brought considerable difficulties in vision-based environmental applications. While, until now, most of the existing environmental monitoring studies are under ordinary conditions, and the studies of complex haze weather conditions have been ignored. Thence, this paper proposes a feature-supervised learning network based on generative adversarial networks (GAN) for environmental monitoring during hazy days. Its main idea is to train the model under the supervision of feature maps from the ground truth. Four key technical contributions are made in the paper. First, pairs of hazy and clean images are used as inputs to supervise the encoding process and obtain high-quality feature maps. Second, the basic GAN formulation is modified by introducing perception loss, style loss, and feature regularization loss to generate better results. Third, multi-scale images are applied as the input to enhance the performance of discriminator. Finally, a hazy remote sensing dataset is created for testing our dehazing method and environmental detection. Extensive experimental results show that the proposed method has achieved better performance than current state-of-the-art methods on both synthetic datasets and real-world remote sensing images.

cs.CV↗

arXiv2020

Conserved quantities in parity-time symmetric systems

Conserved quantities such as energy or the electric charge of a closed system, or the Runge-Lenz vector in Kepler dynamics are determined by its global, local, or accidental symmetries. They were instrumental to advances such as the prediction of neutrinos in the (inverse) beta decay process and the development of self-consistent approximate methods for isolated or thermal many-body systems. In contrast, little is known about conservation laws and their consequences in open systems. Recently, a special class of these systems, called parity-time ($\mathcal{PT}$) symmetric systems, has been intensely explored for their remarkable properties that are absent in their closed counterparts. A complete characterization and observation of conserved quantities in these systems and their consequences is still lacking. Here we present a complete set of conserved observables for a broad class of $\mathcal{PT}$-symmetric Hamiltonians and experimentally demonstrate their properties using single-photon linear optical circuit. By simulating the dynamics of a four-site system across a fourth-order exceptional point, we measure its four conserved quantities and demonstrate their consequences. Our results spell out non-local conservation laws in non-unitary dynamics and provide key elements that will underpin self-consistent analysis of non-Hermitian quantum many-body systems that are forthcoming.

quant-ph↗