arXiv subjects

Wenjing Dai

Publications and source records attributed to Wenjing Dai.

6 recordsLinked to original sources

arXiv2026

Face Normal Estimation from Rags to Riches

Although recent approaches to face normal estimation have achieved promising results, their effectiveness heavily depends on large-scale paired data for training. This paper concentrates on relieving this requirement via developing a coarse-to-fine normal estimator. Concretely, our method first trains a neat model from a small dataset to produce coarse face normals that perform as guidance (called exemplars) for the following refinement. A self-attention mechanism is employed to capture long-range dependencies, thus remedying severe local artifacts left in estimated coarse facial normals. Then, a refinement network is customized for the sake of mapping input face images together with corresponding exemplars to fine-grained high-quality facial normals. Such a logical function split can significantly cut the requirement of massive paired data and computational resource. Extensive experiments and ablation studies are conducted to demonstrate the efficacy of our design and reveal its superiority over state-of-the-art methods in terms of both training expense as well as estimation quality. Our code and models are open-sourced at: https://github.com/AutoHDR/FNR2R.git.

cs.CV↗

arXiv2024

Broadband NIR photon upconversion generates NIR persistent luminescence for bioimaging

Upconversion persistent luminescence (UCPL) phosphors that can be directly charged by near-infrared (NIR) light have gained considerable attention due to their promising applications ranging from photonics to biomedicine. However, current lanthanide-based UCPL phosphors show small absorption cross-sections and low upconversion charging efficiency. The development of UCPL phosphors faces challenges of lacking flexible upconversion charging pathways and poor design flexibility. Herein, we discovered a new lattice defect-mediated broadband photon upconversion process and the accompanied NIR-to-NIR UCPL in Cr-doped zinc gallate nanoparticles. The zinc gallate nanoparticles can be directly activated by broadband NIR light in the 700-1000 nm range to produce persistent luminescence at about 700 nm, which is also readily enhanced by rationally tailoring the lattice defects in the phosphors. This proposed UCPL phosphors achieved a signal-to-background ratio of over 200 in bioimaging by efficiently avoiding interference from autofluorescence and light scattering. Our findings reported the lattice defect-mediated photon upconversion for the first time, which significantly expanded the horizons for the flexible design of NIR-to-NIR UCPL phosphors toward broad applications.

physics.optics↗

arXiv2023

Face Inverse Rendering via Hierarchical Decoupling

Previous face inverse rendering methods often require synthetic data with ground truth and/or professional equipment like a lighting stage. However, a model trained on synthetic data or using pre-defined lighting priors is typically unable to generalize well for real-world situations, due to the gap between synthetic data/lighting priors and real data. Furthermore, for common users, the professional equipment and skill make the task expensive and complex. In this paper, we propose a deep learning framework to disentangle face images in the wild into their corresponding albedo, normal, and lighting components. Specifically, a decomposition network is built with a hierarchical subdivision strategy, which takes image pairs captured from arbitrary viewpoints as input. In this way, our approach can greatly mitigate the pressure from data preparation, and significantly broaden the applicability of face inverse rendering. Extensive experiments are conducted to demonstrate the efficacy of our design, and show its superior performance in face relighting over other state-of-the-art alternatives. {Our code is available at \url{https://github.com/AutoHDR/HD-Net.git}}

cs.CV↗

arXiv2022

Smart Meter Data Anomaly Detection using Variational Recurrent Autoencoders with Attention

In the digitization of energy systems, sensors and smart meters are increasingly being used to monitor production, operation and demand. Detection of anomalies based on smart meter data is crucial to identify potential risks and unusual events at an early stage, which can serve as a reference for timely initiation of appropriate actions and improving management. However, smart meter data from energy systems often lack labels and contain noise and various patterns without distinctively cyclical. Meanwhile, the vague definition of anomalies in different energy scenarios and highly complex temporal correlations pose a great challenge for anomaly detection. Many traditional unsupervised anomaly detection algorithms such as cluster-based or distance-based models are not robust to noise and not fully exploit the temporal dependency in a time series as well as other dependencies amongst multiple variables (sensors). This paper proposes an unsupervised anomaly detection method based on a Variational Recurrent Autoencoder with attention mechanism. with "dirty" data from smart meters, our method pre-detects missing values and global anomalies to shrink their contribution while training. This paper makes a quantitative comparison with the VAE-based baseline approach and four other unsupervised learning methods, demonstrating its effectiveness and superiority. This paper further validates the proposed method by a real case study of detecting the anomalies of water supply temperature from an industrial heating plant.

eess.SP↗

arXiv2020

Three-state quantum walk on the Cayley Graph of the Dihedral Group

The finite dihedral group generated by one rotation and one reflection is the simplest case of the non-abelian group. Cayley graphs are diagrammatic counterparts of groups. In this paper, much attention is given to the Cayley graph of the dihedral group. Considering the characteristics of the elements in the dihedral group, we propose a model of three-state discrete-time quantum walk (DTQW) on the Caylay graph of the dihedral group with Grover coin. We derive analytic expressions for the the position probability distribution and the long-time limit of the return probability starting from the origin. It is shown that the localization effect is governed by the size of the underlying dihedral group, coin operator and initial state. We also numerically investigate the properties of the proposed model via the probability distribution and the time-averaged probability at the designated position. The abundant phenomena of three-state Grover DTQW on the Caylay graph of the dihedral group can help the community to better understand and to develop new quantum algorithms.

quant-ph↗

arXiv2018

Discrete-time Quantum Walk on the Cayley Graph of the Dihedral Group

The finite dihedral group generated by one rotation and one flip is the simplest case of the non-abelian group. Cayley graphs are diagrammatic counterparts of groups. In this paper, much attention is given to the Cayley graph of the dihedral group. Considering the characteristics of the elements in the dihedral group, we conduct the model of discrete-time quantum walk on the Cayley graph of the dihedral group by special coding mode. This construction makes Fourier transformation can be used to carry out spectral analysis of the dihedral quantum walk, i.e. the non-abelian case. Furthermore, the relation between quantum walk without memory on the Cayley graph of the dihedral group and quantum walk with memory on a cycle is discussed, so that we can explore the potential of quantum walks without and with memory. Here, the numerical simulation is carried out to verify the theoretical analysis results and other properties of the proposed model are further studied.

quant-ph↗