arXiv subjects

Shuang Zhao

Publications and source records attributed to Shuang Zhao.

53 records · Page 3Linked to original sources

arXiv2021

Unified Shape and SVBRDF Recovery using Differentiable Monte Carlo Rendering

Reconstructing the shape and appearance of real-world objects using measured 2D images has been a long-standing problem in computer vision. In this paper, we introduce a new analysis-by-synthesis technique capable of producing high-quality reconstructions through robust coarse-to-fine optimization and physics-based differentiable rendering. Unlike most previous methods that handle geometry and reflectance largely separately, our method unifies the optimization of both by leveraging image gradients with respect to both object reflectance and geometry. To obtain physically accurate gradient estimates, we develop a new GPU-based Monte Carlo differentiable renderer leveraging recent advances in differentiable rendering theory to offer unbiased gradients while enjoying better performance than existing tools like PyTorch3D and redner. To further improve robustness, we utilize several shape and material priors as well as a coarse-to-fine optimization strategy to reconstruct geometry. We demonstrate that our technique can produce reconstructions with higher quality than previous methods such as COLMAP and Kinect Fusion.

cs.CV↗

arXiv2021

A Practical Ply-Based Appearance Modeling for Knitted Fabrics

Modeling the geometry and the appearance of knitted fabrics has been challenging due to their complex geometries and interactions with light. Previous surface-based models have difficulties capturing fine-grained knit geometries; Micro-appearance models, on the other hands, typically store individual cloth fibers explicitly and are expensive to be generated and rendered. Further, neither of the models have been matched the photographs to capture both the reflection and the transmission of light simultaneously. In this paper, we introduce an efficient technique to generate knit models with user-specified knitting patterns. Our model stores individual knit plies with fiber-level detailed depicted using normal and tangent mapping. We evaluate our generated models using a wide array of knitting patterns. Further, we compare qualitatively renderings to our models to photos of real samples.

cs.GR↗

arXiv2021

Defect Engineered Room-Temperature Ferromagnetism in Quasi-Two-Dimensional Nitrided CoTa2O6

Thermal ammonolysis of quasi-two-dimensional (quasi-2D) CoTa2O6 yields the O2-/N3- and anionic vacancy ordered Co2+Ta5+2O6-xN2x/3$\Box$x/3 (x $\leq$ 0.15) that exhibits a transition from antiferromagnetism to defect engineered above room-temperature ferromagnetism as evidenced by diffraction, spectroscopic and magnetic characterizations. First-principles calculations reveal the origin of ferromagnetism is a particular CoON configuration with N located at Wyckoff position 8j, which breaks mirror symmetry about ab plane. A pressure-induced electronic phase transition is also predicted at around 24.5 GPa, accompanied by insulator-to-metal transition and magnetic moment vanishing.

cond-mat.mtrl-sci↗

arXiv2020

A Bayesian Inference Framework for Procedural Material Parameter Estimation

Procedural material models have been gaining traction in many applications thanks to their flexibility, compactness, and easy editability. We explore the inverse rendering problem of procedural material parameter estimation from photographs, presenting a unified view of the problem in a Bayesian framework. In addition to computing point estimates of the parameters by optimization, our framework uses a Markov Chain Monte Carlo approach to sample the space of plausible material parameters, providing a collection of plausible matches that a user can choose from, and efficiently handling both discrete and continuous model parameters. To demonstrate the effectiveness of our framework, we fit procedural models of a range of materials---wall plaster, leather, wood, anisotropic brushed metals and layered metallic paints---to both synthetic and real target images.

cs.GR↗

arXiv2020

MaterialGAN: Reflectance Capture using a Generative SVBRDF Model

We address the problem of reconstructing spatially-varying BRDFs from a small set of image measurements. This is a fundamentally under-constrained problem, and previous work has relied on using various regularization priors or on capturing many images to produce plausible results. In this work, we present MaterialGAN, a deep generative convolutional network based on StyleGAN2, trained to synthesize realistic SVBRDF parameter maps. We show that MaterialGAN can be used as a powerful material prior in an inverse rendering framework: we optimize in its latent representation to generate material maps that match the appearance of the captured images when rendered. We demonstrate this framework on the task of reconstructing SVBRDFs from images captured under flash illumination using a hand-held mobile phone. Our method succeeds in producing plausible material maps that accurately reproduce the target images, and outperforms previous state-of-the-art material capture methods in evaluations on both synthetic and real data. Furthermore, our GAN-based latent space allows for high-level semantic material editing operations such as generating material variations and material morphing.

cs.CV↗

arXiv2020

Online User-AP Association with Predictive Scheduling in Wireless Caching Networks

For wireless caching networks, the scheme design for content delivery is non-trivial in the face of the following tradeoff. On one hand, to optimize overall throughput, users can associate their nearby APs with great channel capacities; however, this may lead to unstable queue backlogs on APs and prolong request delays. On the other hand, to ensure queue stability, some users may have to associate APs with inferior channel states, which would incur throughput loss. Moreover, for such systems, how to conduct predictive scheduling to reduce delays and the fundamental limits of its benefits remain unexplored. In this paper, we formulate the problem of online user-AP association and resource allocation for content delivery with predictive scheduling under a fixed content placement as a stochastic network optimization problem. By exploiting its unique structure, we transform the problem into a series of modular maximization sub-problems with matroid constraints. Then we devise PUARA, a Predictive User-AP Association and Resource Allocation scheme which achieves a provably near-optimal throughput with queue stability. Our theoretical analysis and simulation results show that PUARA can not only perform a tunable control between throughput maximization and queue stability but also incur a notable delay reduction with predicted information.

cs.NI↗

arXiv2019

On the Optical Accuracy of the Salvator Mundi

A debate in the scientific literature has arisen regarding whether the orb depicted in Salvator Mundi, which has been attributed by some experts to Leonardo da Vinci, was rendered in a optically faithful manner or not. Some hypothesize that it was solid crystal while others hypothesize that it was hollow, with competing explanations for its apparent lack of background distortion and its three white spots. In this paper, we study the optical accuracy of the Salvator Mundi using physically based rendering, a sophisticated computer graphics tool that produces optically accurate images by simulating light transport in virtual scenes. We created a virtual model of the composition centered on the translucent orb in the subject's hand. By synthesizing images under configurations that vary illuminations and orb material properties, we tested whether it is optically possible to produce an image that renders the orb similarly to how it appears in the painting. Our experiments show that an optically accurate rendering qualitatively matching that of the painting is indeed possible using materials, light sources, and scientific knowledge available to Leonardo da Vinci circa 1500. We additionally tested alternative theories regarding the composition of the orb, such as that it was a solid calcite ball, which provide empirical evidence that such alternatives are unlikely to produce images similar to the painting, and that the orb is instead hollow.

cs.GR↗

arXiv2019

Mechanics-Aware Modeling of Cloth Appearance

Micro-appearance models have brought unprecedented fidelity and details to cloth rendering. Yet, these models neglect fabric mechanics: when a piece of cloth interacts with the environment, its yarn and fiber arrangement usually changes in response to external contact and tension forces. Since subtle changes of a fabric's microstructures can greatly affect its macroscopic appearance, mechanics-driven appearance variation of fabrics has been a phenomenon that remains to be captured. We introduce a mechanics-aware model that adapts the microstructures of cloth yarns in a physics-based manner. Our technique works on two distinct physical scales: using physics-based simulations of individual yarns, we capture the rearrangement of yarn-level structures in response to external forces. These yarn structures are further enriched to obtain appearance-driving fiber-level details. The cross-scale enrichment is made practical through a new parameter fitting algorithm for simulation, an augmented procedural yarn model coupled with a custom-design regression neural network. We train the network using a dataset generated by joint simulations at both the yarn and the fiber levels. Through several examples, we demonstrate that our model is capable of synthesizing photorealistic cloth appearance in a %dynamic and mechanically plausible way.

cs.GR↗

arXiv2019

News Cover Assessment via Multi-task Learning

Online personalized news product needs a suitable cover for the article. The news cover demands to be with high image quality, and draw readers' attention at same time, which is extraordinary challenging due to the subjectivity of the task. In this paper, we assess the news cover from image clarity and object salience perspective. We propose an end-to-end multi-task learning network for image clarity assessment and semantic segmentation simultaneously, the results of which can be guided for news cover assessment. The proposed network is based on a modified DeepLabv3+ model. The network backbone is used for multiple scale spatial features exaction, followed by two branches for image clarity assessment and semantic segmentation, respectively. The experiment results show that the proposed model is able to capture important content in images and performs better than single-task learning baselines on our proposed game content based CIA dataset.

cs.CV↗

arXiv2018

Inverse Transport Networks

We introduce inverse transport networks as a learning architecture for inverse rendering problems where, given input image measurements, we seek to infer physical scene parameters such as shape, material, and illumination. During training, these networks are evaluated not only in terms of how close they can predict groundtruth parameters, but also in terms of whether the parameters they produce can be used, together with physically-accurate graphics renderers, to reproduce the input image measurements. To en- able training of inverse transport networks using stochastic gradient descent, we additionally create a general-purpose, physically-accurate differentiable renderer, which can be used to estimate derivatives of images with respect to arbitrary physical scene parameters. Our experiments demonstrate that inverse transport networks can be trained efficiently using differentiable rendering, and that they generalize to scenes with completely unseen geometry and illumination better than networks trained without appearance- matching regularization.

cs.CV↗

arXiv2017

On the forcing spectrum of generalized Petersen graphs P(n,2)

The forcing number of a perfect matching $M$ of a graph $G$ is the smallest cardinality of subsets of $M$ that are contained in no other perfect matchings of $G$. The forcing spectrum of $G$ is the collection of forcing numbers of all perfect matchings of $G$. In this paper, we classify the perfect matchings of a generalized Petersen graph $P(n,2)$ in two types, and show that the forcing spectrum is the union of two integer intervals. For $n\ge 34$, it is $\left[\lceil \frac { n }{ 12 } \rceil+1,\lceil \frac { n+3 }{ 7 } \rceil +δ(n)\right]\cup \left[\lceil \frac { n+2 }{ 6 } \rceil,\lceil \frac { n }{ 4 } \rceil\right]$, where $δ(n)=1$ if $n\equiv 3$ (mod 7), and $δ(n)=0$ otherwise.

math.CO↗

arXiv2016

Inverse Diffusion Curves using Shape Optimization

The inverse diffusion curve problem focuses on automatic creation of diffusion curve images that resemble user provided color fields. This problem is challenging since the 1D curves have a nonlinear and global impact on resulting color fields via a partial differential equation (PDE). We introduce a new approach complementary to previous methods by optimizing curve geometry. In particular, we propose a novel iterative algorithm based on the theory of shape derivatives. The resulting diffusion curves are clean and well-shaped, and the final image closely approximates the input. Our method provides a user-controlled parameter to regularize curve complexity, and generalizes to handle input color fields represented in a variety of formats.

cs.GR↗

arXiv2014

Wavelength conversion and parametric amplification of optical pulses via quasi-phase-matched FWM in long-period Bragg silicon waveguides

We present a theoretical analysis supported by comprehensive numerical simulations of quasi phase-matched four-wave mixing (FWM) of ultrashort optical pulses that propagate in weakly width-modulated silicon photonic nanowire gratings. Our study reveals that, by properly designing the optical waveguide such that the interacting pulses co-propagate with the same group-velocity, a conversion efficiency enhancement of more than 15 dB, as compared to a uniform waveguide, can readily be achieved. We also analyze the dependence of the conversion efficiency and FWM gain on the pulse width, time delay, walk-off parameter, and grating modulation depth.

physics.optics↗

arXiv2007

Event-by-event simulation of Einstein-Podolsky-Rosen-Bohm experiments

We construct an event-based computer simulation model of the Einstein-Podolsky-Rosen-Bohm experiments with photons. The algorithm is a one-to-one copy of the data gathering and analysis procedures used in real laboratory experiments. We consider two types of experiments, those with a source emitting photons with opposite but otherwise unpredictable polarization and those with a source emitting photons with fixed polarization. In the simulation, the choice of the direction of polarization measurement for each detection event is arbitrary. We use three different procedures to identify pairs of photons and compute the frequency of coincidences by analyzing experimental data and simulation data. The model strictly satisfies Einstein's criteria of local causality, does not rely on any concept of quantum theory and reproduces the results of quantum theory for both types of experiments. We give a rigorous proof that the probabilistic description of the simulation model yields the quantum theoretical expressions for the single- and two-particle expectation values.

quant-ph↗

arXiv2007

Event-by-event Simulation of Quantum Cryptography Protocols

We present a new approach to simulate quantum cryptography protocols using event-based processes. The method is validated by simulating the BB84 protocol and the Ekert protocol, both without and with the presence of an eavesdropper.

quant-ph↗

arXiv2007

Single production of the doubly charged scalar in the littlest Higgs model

Single production of the doubly charged scalars $Φ^{\pm\pm}$ via $eγ$, $ep$ and $pp$ collisions is studied in the context of the little Higgs$(LH)$ model. Our numerical results show that the new particles $Φ^{\pm\pm}$ can be abundantly produced and their possible signatures should be detected in future high energy linear $e^{+}e^{-}$ collider$(ILC)$. The cross section for single production of $Φ^{\pm\pm}$ at the $LHC$ is much smaller than that at the $ILC$ or the $THERA$.

hep-ph↗

arXiv2007

Lepton flavor violating signals of a little Higgs model at the high energy linear $e^{+}e^{-}$ colliders

Littlest Higgs $(LH)$ model predicts the existence of the doubly charged scalars $Φ^{\pm\pm}$, which generally have large flavor changing couplings to leptons. We calculate the contributions of $Φ^{\pm\pm}$ to the lepton flavor violating $(LFV)$ processes $l_{i}\to l_{j}γ$ and $l_{i}\to l_{j}l_{k}l_{k}$, and compare our numerical results with the current experimental upper limits on these processes. We find that some of these processes can give severe constraints on the coupling constant $Y_{ij}$ and the mass parameter $M_Φ$. Taking into account the constraints on these free parameters, we further discuss the possible lepton flavor violating signals of $Φ^{\pm\pm}$ at the high energy linear $e^{+}e^{-}$ collider $(ILC)$ experiments. Our numerical results show that the possible signals of $Φ^{\pm\pm}$ might be detected via the subprocesses $e^{\pm}e^{\pm}\to l^{\pm}l^{\pm}$ in the future $ILC$ experiments.

hep-ph↗