arXiv subjects

Jianing Zhang

Publications and source records attributed to Jianing Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

3M-TI: High-Quality Mobile Thermal Imaging via Calibration-free Multi-Camera Cross-Modal Diffusion

The miniaturization of thermal sensors for mobile platforms inherently limits their spatial resolution and textural fidelity, leading to blurry and less informative images. Existing thermal super-resolution (SR) methods can be grouped into single-image and RGB-guided approaches: the former struggles to recover fine structures from limited information, while the latter relies on accurate and laborious cross-camera calibration, which hinders practical deployment and robustness. Here, we propose 3M-TI, a calibration-free Multi-camera cross-Modality diffusion framework for Mobile Thermal Imaging. At its core, 3M-TI integrates a cross-modal self-attention module (CSM) into the diffusion UNet, replacing the original self-attention layers to adaptively align thermal and RGB features throughout the denoising process, without requiring explicit camera calibration. This design enables the diffusion network to leverage its generative prior to enhance spatial resolution, structural fidelity, and texture detail in the super-resolved thermal images. Extensive evaluations on real-world mobile thermal cameras and public benchmarks validate our superior performance, achieving state-of-the-art results in both visual quality and quantitative metrics. More importantly, the thermal images enhanced by 3M-TI lead to substantial gains in critical downstream tasks like object detection and segmentation, underscoring its practical value for robust mobile thermal perception systems. More materials: https://github.com/work-submit/3MTI.

cs.CV↗

arXiv2026

A physics-inspired nonlinear momentum method for gradient descent with applications to inverse photonic design

In this work, a nonlinear momentum method is introduced to enhance the convergence performance of momentum-based gradient optimization algorithms. Classical momentum methods, such as the Heavy Ball method, can be viewed as a dynamical system with quadratic kinetic energy and linear damping. By extending this analogy to non-Newtonian dynamical systems, we construct a Hamiltonian framework for optimization problems. In this framework, nonlinear kinetic energy and nonlinear damping effects naturally emerge. It provides a more flexible and physically interpretable mechanism for optimization algorithms. Specifically, we employ an anharmonic kinetic energy function to capture the inertial effects of accumulated gradient information during the optimization process, while the nonlinear damping mechanism effectively regulates the contribution of momentum during convergence. Numerical experiments show that the proposed method achieves faster convergence compared to classical momentum algorithms, making it particularly suitable for inverse design tasks. Moreover, the Hamiltonian based algorithmic framework may offer physical insights for the development of efficient physics-inspired optimization algorithms.

physics.comp-ph↗

arXiv2025

Communication-Efficient and Differentially Private Vertical Federated Learning with Zeroth-Order Optimization

Vertical Federated Learning (VFL) enables collaborative model training across feature-partitioned devices, yet its reliance on device-server information exchange introduces significant communication overhead and privacy risks. Downlink communication from the server to devices in VFL exposes gradient-related signals of the global loss that can be leveraged in inference attacks. Existing privacy-preserving VFL approaches that inject differential privacy (DP) noise on the downlink have the natural repercussion of degraded gradient quality, slowed convergence, and excessive communication rounds. In this work, we propose DPZV, a communication-efficient and differentially private ZO-VFL framework with tunable privacy guarantees. Based on zeroth-order (ZO) optimization, DPZV injects calibrated scalar-valued DP noise on the downlink, significantly reducing variance amplification while providing equivalent protection against targeted inference attacks. Through rigorous theoretical analysis, we establish convergence guarantees comparable to first-order DP-SGD, despite relying solely on ZO estimators, and prove that DPZV satisfies $(ε, δ)$-DP. Extensive experiments demonstrate that DPZV consistently achieves a superior privacy-utility tradeoff and requires fewer communication rounds than existing DP-VFL baselines under strict privacy constraints ($ε\leq 10$).

cs.LG↗

arXiv2025

A modified recursive transfer matrix algorithm for radiation and scattering computation of a multilayer sphere

We discuss the electromagnetic scattering and radiation problems of multilayered spheres, reviewing the history of the Lorentz-Mie theory and the numerical stability issues encountered in handling multilayered spheres. By combining recursive methods with the transfer matrix method, we propose a modified transfer matrix algorithm designed for the stable and efficient calculation of electromagnetic scattering coefficients of multilayered spheres. The new algorithm simplifies the recursive formulas by introducing Debye potentials and logarithmic derivatives, effectively avoiding numerical overflow issues associated with Bessel functions under large complex variables. Moreover, by adopting a hybrid recursive strategy, this algorithm can resolve the singularity problem associated with logarithmic derivatives in previous algorithms. Numerical test results demonstrate that this algorithm offers superior stability and applicability when dealing with complex cases such as thin shells and strongly absorbing media.

physics.comp-ph↗

arXiv2025

Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approach

Split Federated Learning (SFL) enables scalable training on edge devices by combining the parallelism of Federated Learning (FL) with the computational offloading of Split Learning (SL). Despite its great success, SFL suffers significantly from the well-known straggler issue in distributed learning systems. This problem is exacerbated by the dependency between Split Server and clients: the Split Server side model update relies on receiving activations from clients. Such synchronization requirement introduces significant time latency, making straggler a critical bottleneck to the scalability and efficiency of the system. To mitigate this problem, we propose MU-SplitFed, a straggler-resilient SFL algorithm in zeroth-order optimization that decouples training progress from straggler delays via a simple yet effective unbalanced update mechanism. By enabling the server to perform $τ$ local updates per client round, MU-SplitFed achieves a convergence rate of $O(\sqrt{d/(τT)})$ for non-convex objectives, demonstrating a linear speedup of $τ$ in communication rounds. Experiments demonstrate that MU-SplitFed consistently outperforms baseline methods with the presence of stragglers and effectively mitigates their impact through adaptive tuning of $τ$. The code for this project is available at https://github.com/Johnny-Zip/MU-SplitFed.

cs.DC↗

arXiv2025

Sub-ppb CO2 Detection based on Dissipative Whispering Gallery mode Microcavity Sensor

Whispering gallery mode (WGM) microcavities feature ultrahigh Q-factors and small mode volumes, offering strong light-matter interactions for sensing applications. However, unmodified surfaces are weakly responsive togas-phase refractive index changes, limiting trace gas detection. In this work, we propose a novel dissipative sensing scheme based on a non-functionalized WGM microcavity and experimentally demonstrate its feasibility and performance through trace-level CO2 detection. Unlike conventional dispersive sensing that tracks resonance frequency shifts, our approach leverages enhanced local fields and thermal effects at the coupling region to convert weak absorption into measurable variations in resonance depth. A modulation-demodulation method suppresses low-frequency noise, with parameters optimized experimentally. The sensor achieves quantitative detection over 1.5-400 ppm (R2 > 0.99), ~1.13% accuracy, a minimum detection limit of 0.12 ppb at 424 s integration-five orders of magnitude better than dispersive WGM sensors. Long term CO2 monitoring further demonstrates stability and resistance to environmental perturbations. Compared with state-of-the-art cavity-enhanced and photoacoustic sensors, our system delivers at least an order of magnitude lower baseline detection while maintaining compact size, ambient pressure operation, and low cost, highlighting its potential for scalable, real-world deployment.

physics.optics↗

arXiv2025

On-chip amplification-free fCEO detection and broadband SCG in parabolically width-modulated TFLN waveguides

We demonstrate amplification-free carrier-envelope offset (fCEO) detection in parabolically width-modulated z-cut thin-film lithium niobate (TFLN) waveguide that simultaneously engineers dispersion and enhances nonlinear interactions. With 116 fs pulses at 1560 nm, the device generates more than two octaves broadband SCG spanning 600 to beyond 2400 nm, enabling spectral overlap between dispersive waves and second-harmonic generation near 780 nm for robust f-2f self-referencing. Most notably, we achieve the first fully amplification-free, on-chip fCEO detection without optical or electronic amplifiers, obtaining 34 dB SNR at 100 kHz RBW and 57 dB at 100 Hz RBW, the highest reported to date under such conditions. These results establish a new benchmark for scalable, power-efficient, self-referenced frequency combs and quantum-enabled photonic systems.

physics.optics↗

arXiv2025

GBR: Generative Bundle Refinement for High-fidelity Gaussian Splatting with Enhanced Mesh Reconstruction

Gaussian splatting has gained attention for its efficient representation and rendering of 3D scenes using continuous Gaussian primitives. However, it struggles with sparse-view inputs due to limited geometric and photometric information, causing ambiguities in depth, shape, and texture. we propose GBR: Generative Bundle Refinement, a method for high-fidelity Gaussian splatting and meshing using only 4-6 input views. GBR integrates a neural bundle adjustment module to enhance geometry accuracy and a generative depth refinement module to improve geometry fidelity. More specifically, the neural bundle adjustment module integrates a foundation network to produce initial 3D point maps and point matches from unposed images, followed by bundle adjustment optimization to improve multiview consistency and point cloud accuracy. The generative depth refinement module employs a diffusion-based strategy to enhance geometric details and fidelity while preserving the scale. Finally, for Gaussian splatting optimization, we propose a multimodal loss function incorporating depth and normal consistency, geometric regularization, and pseudo-view supervision, providing robust guidance under sparse-view conditions. Experiments on widely used datasets show that GBR significantly outperforms existing methods under sparse-view inputs. Additionally, GBR demonstrates the ability to reconstruct and render large-scale real-world scenes, such as the Pavilion of Prince Teng and the Great Wall, with remarkable details using only 6 views.

cs.CV↗

arXiv2025

SurGSplat: Progressive Geometry-Constrained Gaussian Splatting for Surgical Scene Reconstruction

Intraoperative navigation relies heavily on precise 3D reconstruction to ensure accuracy and safety during surgical procedures. However, endoscopic scenarios present unique challenges, including sparse features and inconsistent lighting, which render many existing Structure-from-Motion (SfM)-based methods inadequate and prone to reconstruction failure. To mitigate these constraints, we propose SurGSplat, a novel paradigm designed to progressively refine 3D Gaussian Splatting (3DGS) through the integration of geometric constraints. By enabling the detailed reconstruction of vascular structures and other critical features, SurGSplat provides surgeons with enhanced visual clarity, facilitating precise intraoperative decision-making. Experimental evaluations demonstrate that SurGSplat achieves superior performance in both novel view synthesis (NVS) and pose estimation accuracy, establishing it as a high-fidelity and efficient solution for surgical scene reconstruction. More information and results can be found on the page https://surgsplat.github.io/.

cs.GR↗

arXiv2025

Degradation-Modeled Multipath Diffusion for Tunable Metalens Photography

Metalenses offer significant potential for ultra-compact computational imaging but face challenges from complex optical degradation and computational restoration difficulties. Existing methods typically rely on precise optical calibration or massive paired datasets, which are non-trivial for real-world imaging systems. Furthermore, a lack of control over the inference process often results in undesirable hallucinated artifacts. We introduce Degradation-Modeled Multipath Diffusion for tunable metalens photography, leveraging powerful natural image priors from pretrained models instead of large datasets. Our framework uses positive, neutral, and negative-prompt paths to balance high-frequency detail generation, structural fidelity, and suppression of metalens-specific degradation, alongside \textit{pseudo} data augmentation. A tunable decoder enables controlled trade-offs between fidelity and perceptual quality. Additionally, a spatially varying degradation-aware attention (SVDA) module adaptively models complex optical and sensor-induced degradation. Finally, we design and build a millimeter-scale MetaCamera for real-world validation. Extensive results show that our approach outperforms state-of-the-art methods, achieving high-fidelity and sharp image reconstruction. More materials: https://dmdiff.github.io/.

cs.CV↗

arXiv2025

Gradient Correction in Federated Learning with Adaptive Optimization

In federated learning (FL), model training performance is strongly impacted by data heterogeneity across clients. Client-drift compensation methods have recently emerged as a solution to this issue, introducing correction terms into local model updates. To date, these methods have only been considered under stochastic gradient descent (SGD)-based model training, while modern FL frameworks also employ adaptive optimizers (e.g., Adam) for improved convergence. However, due to the complex interplay between first and second moments found in most adaptive optimization methods, naively injecting correction terms can lead to performance degradation in heterogeneous settings. In this work, we propose {\tt FAdamGC}, the first algorithm to integrate drift compensation into adaptive federated optimization. The key idea of {\tt FAdamGC} is injecting a pre-estimation correction term that aligns with the moment structure of adaptive methods. We provide a rigorous convergence analysis of our algorithm under non-convex settings, showing that {\tt FAdamGC} results in better rate and milder assumptions than naively porting SGD-based correction algorithms into adaptive optimizers. Our experimental results demonstrate that {\tt FAdamGC} consistently outperform existing methods in total communication and computation cost across varying levels of data heterogeneity, showing the efficacy of correcting gradient information in federated adaptive optimization.

cs.LG↗

arXiv2024

Anomalous photo-induced band renormalization in correlated materials: Case study of Ta$_2$NiSe$_5$

We investigate the anomalous photo-induced band renormalization in correlated materials, exemplified by the case of Ta$_2$NiSe$_5$. The manifestation of this anomaly is characterized by the alternating direction of band shift in response to changes in the laser parameters or electron momentum. We attribute the phenomena to the band inversion of the material and the selective excitation of a high-lying flat band, leading to the competition between the Hartree shift and the order collapse. These findings are based on {\it ab initio} determined effective model for Ta$_2$NiSe$_5$, in which we incorporate high-lying states and the time-dependent GW simulation to follow the non-equilibrium dynamics induced by the laser. Our findings reveal the sensitivity of the non-equilibrium electronic dynamics to the band structure and laser protocols, providing valuable guidance for the selection of suitable materials and lasers in the engineering of band structures.

cond-mat.str-el↗

arXiv2023

Laser frequency stabilization and photoacoustic detection based on the tapered fiber coupled crystalline resonator

We demonstrate laser frequency stabilization using a high-Q MgF2 crystalline whispering gallery mode resonator coupled with a tapered fiber. We discovered that the tapered fiber, acting as a microcantilever, exhibits mechanical resonance characteristics that is capable of transmitting acoustic perturbations to the frequency locking loop. Both experimental and theoretical investigations into the influence of external acoustic waves on the coupling system were conducted. After acoustic isolation, the locked laser exhibits a minimum frequency noise of 0.4Hz2/Hz at 7kHz and an integral linewidth of 68Hz (0.1s integration time). Benefiting from the ultralow frequency noise of the stabilized laser, it achieves a minimum noise equivalent acoustic signal level of 4.76*10-4 Pa/Hz1/2. Our results not only facilitate the realization of ultralow noise lasers but also serves as a novel and sensitive photoacoustic detector.

physics.optics↗

arXiv2021

High power 1640-nm Er:Y2O3 ceramic laser at room temperature

We report on high power operation of Er:Y2O3 ceramic laser at ~1.6 μm using low scattering loss, 0.25 at.% Er3+ doped ceramic sample fabricated in-house via co-precipitation process. The laser is in-band pumped by an Er, Yb fiber laser at 1535.6 nm and generates 10.2 W of continuous-wave (CW) output power at 1640.4 nm with a slope efficiency of 25% with respect to the absorbed pump power. To the best of our knowledge, this is the first demonstration of ~1.6 μm Er:Y2O3 laser at room temperature. The prospects for further scaling in output power and lasing efficiency via low Er3+ doping and reduced energy-transfer upconversion are discussed.

physics.optics↗

arXiv2021

LEAD: LiDAR Extender for Autonomous Driving

3D perception using sensors under vehicle industrial standard is the rigid demand in autonomous driving. MEMS LiDAR emerges with irresistible trend due to its lower cost, more robust, and meeting the mass-production standards. However, it suffers small field of view (FoV), slowing down the step of its population. In this paper, we propose LEAD, i.e., LiDAR Extender for Autonomous Driving, to extend the MEMS LiDAR by coupled image w.r.t both FoV and range. We propose a multi-stage propagation strategy based on depth distributions and uncertainty map, which shows effective propagation ability. Moreover, our depth outpainting/propagation network follows a teacher-student training fashion, which transfers depth estimation ability to depth completion network without any scale error passed. To validate the LiDAR extension quality, we utilize a high-precise laser scanner to generate a ground-truth dataset. Quantitative and qualitative evaluations show that our scheme outperforms SOTAs with a large margin. We believe the proposed LEAD along with the dataset would benefit the community w.r.t depth researches.

cs.CV↗

arXiv2019

On sampling of scattering phase functions

Monte Carlo radiative transfer, which has been demonstrated as a successful algorithm for modeling radiation transport through the astrophysical medium, relies on sampling of scattering phase functions. We review several classic sampling algorithms such as the tabulated method and the accept-reject method for sampling the scattering phase function. The tabulated method uses a piecewise constant approximation for the true scattering phase function; we improve its sampling performance on a small scattering angle by using piecewise linear and piecewise log-linear approximations. It has previously been believed that certain complicated analytic phase functions such as the Fournier-Forand phase function cannot be simulated without approximations. We show that the tabulated method combined with the accept-reject method can be applied to sample such complicated scattering phase functions accurately. Furthermore, we introduce the Gibbs sampling method for sampling complicated approximate analytic phase functions. In addition, we propose a new modified Henyey-Greenstein phase function with exponential decay terms for modeling realistic dust scattering. Based on Monte Carlo simulations of radiative transfer through a plane-parallel medium, we also demonstrate that the result simulated with the new phase function can provide a good fit to the result simulated with the realistic dust phase function.

physics.comp-ph↗

arXiv2017

Geometric modeling of aerosol surface roughness and numerical simulation of its impact on aerosol optical properties

A stochastic method is introduced for geometric modeling aerosol surface roughness with random field and discrete differential geometry theory. Optical scattering properties are computed for randomly oriented spheroidal particles with uniformly random surface roughness. Invariant imbedding T-Matrix and geometric optics method are applied to compute light scattering properties of aerosol particles covered from Rayleigh to geometric optics region. We simulatied scattering phase matrix of model particles, better performace is obtained than smooth particles. We aslo introduce introduce entropy and relative entropy as measures to distinguish the optical scattering similarities between different particles.

physics.ao-ph↗

arXiv2016

Time-consistency of risk measures with GARCH volatilities and their estimation

In this paper we study time-consistent risk measures for returns that are given by a GARCH(1,1) model. We present a construction of risk measures based on their static counterparts that overcomes the lack of time-consistency. We then study in detail our construction for the risk measures Value-at-Risk (VaR) and Average Value-at-Risk (AVaR). While in the VaR case we can derive an analytical formula for its time-consistent counterpart, in the AVaR case we derive lower and upper bounds to its time-consistent version. Furthermore, we incorporate techniques from Extreme Value Theory (EVT) to allow for a more tail-geared statistical analysis of the corresponding risk measures. We conclude with an application of our results to a data set of stock prices.

q-fin.RM↗