arXiv subjects

Jun Qiu

Publications and source records attributed to Jun Qiu.

15 recordsLinked to original sources

arXiv2026

Fast Implicit Neural Light Field Representation via Geometric Decomposition and Multi-Resolution Low-Rank Features

Implicit neural representations provide a compact and continuous way to reconstruct dense light fields from sampled ray coordinates. However, fast light field reconstruction remains challenging because a light field is a high-dimensional signal with strong spatial-angular redundancy and structured disparity variations. Directly fitting 4D ray coordinates with a neural network often requires considerable optimization time to recover both view appearance and cross-view consistency. To address this issue, this paper proposes a fast implicit light field representation based on geometric decomposition and multi-resolution low-rank features. The proposed method decomposes a 4D light field into a horizontal disparity plane, a spatial texture plane, and a vertical disparity plane. Each plane is represented by a low-rank structure that combines a low-resolution 2D grid with the element-wise product of two high-resolution 1D line features at multiple resolution levels. The fused features are decoded by a lightweight multilayer perceptron to predict RGB values. Experiments on public light field datasets show that the proposed method achieves competitive reconstruction quality while providing a better trade-off among model parameters, training time, and inference efficiency.

cs.CV↗

arXiv2026

Frequency-Decomposed INR for NIR-Assisted Low-Light RGB Image Denoising

Addressing the issues of severe noise and high frequency structural degradation in visible images under low-light conditions, this paper proposes a Near Infrared (NIR) aided low light image restoration method based on Frequency Decoupled Implicit Neural Representation (FDINR). Based on the statistical prior of RGB-NIR cross-modal frequency correlations, specifically that low-frequency RGB signals are more reliable, whereas high frequency NIR signals exhibit higher correlation, we explicitly decompose images into distinct frequency components via multi-scale wavelet transforms and construct a dual-branch implicit neural representation framework. Within this framework, we design a cross modal differentiated frequency supervision mechanism, leveraging low light RGB to guide the reconstruction of low frequency luminance and color, and utilizing high-SNR NIR signals to constrain the generation of high frequency texture details, thereby achieving complementary advantages in the frequency domain. Furthermore, an uncertainty-based adaptive weighting loss function is introduced to automatically balance the contributions of different frequency tasks, solving the problems of color distortion and artifacts caused by rigid fusion in the spatial domain common in traditional methods. Experimental results demonstrate that FD-INR not only effectively restores image luminance consistency and structural details but also, benefitting from its implicit continuous representation, outperforms existing methods in arbitrary-resolution reconstruction tasks, significantly enhancing the reliability of low light perception.

cs.CV↗

arXiv2026

Adaptive Local Frequency Filtering for Fourier-Encoded Implicit Neural Representations

Fourier-encoded implicit neural representations (INRs) have shown strong capability in modeling continuous signals from discrete samples. However, conventional Fourier feature mappings use a fixed set of frequencies over the entire spatial domain, making them poorly suited to signals with spatially varying local spectra and often leading to slow convergence of high-frequency details. To address this issue, we propose an adaptive local frequency filtering method for Fourier-encoded INRs. The proposed method introduces a spatially varying parameter $\alpha(\mathbf{x})$ to modulate encoded Fourier components, enabling a smooth transition among low-pass, band-pass, and high-pass behaviors at different spatial locations. We further analyze the effect of the proposed filter from the neural tangent kernel (NTK) perspective and provide an NTK-inspired interpretation of how it reshapes the effective kernel spectrum. Experiments on 2D image fitting, 3D shape representation, and sparse data reconstruction demonstrate that the proposed method consistently improves reconstruction quality and leads to faster optimization compared with fixed-frequency baselines. In addition, the learned $\alpha(\mathbf{x})$ provides an intuitive visualization of spatially varying frequency preferences, which helps explain the behavior of the model on non-stationary signals. These results indicate that adaptive local frequency modulation is a practical enhancement for Fourier-encoded INRs.

cs.CV↗

arXiv2026

Towards Personalized Multi-Modal MRI Synthesis across Heterogeneous Datasets

Synthesizing missing modalities in multi-modal magnetic resonance imaging (MRI) is vital for ensuring diagnostic completeness, particularly when full acquisitions are infeasible due to time constraints, motion artifacts, and patient tolerance. Recent unified synthesis models have enabled flexible synthesis tasks by accommodating various input-output configurations. However, their training and evaluation are typically restricted to a single dataset, limiting their generalizability across diverse clinical datasets and impeding practical deployment. To address this limitation, we propose PMM-Synth, a personalized MRI synthesis framework that not only supports various synthesis tasks but also generalizes effectively across heterogeneous datasets. PMM-Synth is jointly trained on multiple multi-modal MRI datasets that differ in modality coverage, disease types, and intensity distributions. It achieves cross-dataset generalization through three core innovations: a Personalized Feature Modulation module that dynamically adapts feature representations based on dataset identifier to mitigate the impact of distributional shifts; a Modality-Consistent Batch Scheduler that facilitates stable and efficient batch training under inconsistent modality conditions; and a selective supervision loss to ensure effective learning when ground truth modalities are partially missing. Evaluated on four clinical multi-modal MRI datasets, PMM-Synth consistently outperforms state-of-the-art methods in both one-to-one and many-to-one synthesis tasks, achieving superior PSNR and SSIM scores. Qualitative results further demonstrate improved preservation of anatomical structures and pathological details. Additionally, downstream tumor segmentation and radiological reporting studies suggest that PMM-Synth holds potential for supporting reliable diagnosis under real-world modality-missing scenarios.

cs.CV↗

arXiv2025

Partial sums of the hyperharmonic series

In 1946, Erd\"os and Niven proved that no two partial sums of the harmonic series are equal. In this paper, we extend this result by demonstrating that no two partial sums of the hyperharmonic series are equal.

math.NT↗

arXiv2025

Infrared and Visible Image Fusion Based on Implicit Neural Representations

Infrared and visible light image fusion aims to combine the strengths of both modalities to generate images that are rich in information and fulfill visual or computational requirements. This paper proposes an image fusion method based on Implicit Neural Representations (INR), referred to as INRFuse. This method parameterizes a continuous function through a neural network to implicitly represent the multimodal information of the image, breaking through the traditional reliance on discrete pixels or explicit features. The normalized spatial coordinates of the infrared and visible light images serve as inputs, and multi-layer perceptrons is utilized to adaptively fuse the features of both modalities, resulting in the output of the fused image. By designing multiple loss functions, the method jointly optimizes the similarity between the fused image and the original images, effectively preserving the thermal radiation information of the infrared image while maintaining the texture details of the visible light image. Furthermore, the resolution-independent characteristic of INR allows for the direct fusion of images with varying resolutions and achieves super-resolution reconstruction through high-density coordinate queries. Experimental results indicate that INRFuse outperforms existing methods in both subjective visual quality and objective evaluation metrics, producing fused images with clear structures, natural details, and rich information without the necessity for a training dataset.

cs.CV↗

arXiv2025

Incomplete Data Multi-Source Static Computed Tomography Reconstruction with Diffusion Priors and Implicit Neural Representation

The dose of X-ray radiation and the scanning time are crucial factors in computed tomography (CT) for clinical applications. In this work, we introduce a multi-source static CT imaging system designed to rapidly acquire sparse view and limited angle data in CT imaging, addressing these critical factors. This linear imaging inverse problem is solved by a conditional generation process within the denoising diffusion image reconstruction framework. The noisy volume data sample generated by the reverse time diffusion process is projected onto the affine set to ensure its consistency to the measured data. To enhance the quality of the reconstruction, the 3D phantom's orthogonal space projector is parameterized implicitly by a neural network. Then, a self-supervised learning algorithm is adopted to optimize the implicit neural representation. Through this multistage conditional generation process, we obtain a new approximate posterior sampling strategy for MSCT volume reconstruction. Numerical experiments are implemented with various imaging settings to verify the effectiveness of our methods for incomplete data MSCT volume reconstruction.

physics.med-ph↗

arXiv2024

Iterative approach to reconstructing neural disparity fields from light-field data

This study proposes a neural disparity field (NDF) that establishes an implicit, continuous representation of scene disparity based on a neural field and an iterative approach to address the inverse problem of NDF reconstruction from light-field data. NDF enables seamless and precise characterization of disparity variations in three-dimensional scenes and can discretize disparity at any arbitrary resolution, overcoming the limitations of traditional disparity maps that are prone to sampling errors and interpolation inaccuracies. The proposed NDF network architecture utilizes hash encoding combined with multilayer perceptrons to capture detailed disparities in texture levels, thereby enhancing its ability to represent the geometric information of complex scenes. By leveraging the spatial-angular consistency inherent in light-field data, a differentiable forward model to generate a central view image from the light-field data is developed. Based on the forward model, an optimization scheme for the inverse problem of NDF reconstruction using differentiable propagation operators is established. Furthermore, an iterative solution method is adopted to reconstruct the NDF in the optimization scheme, which does not require training datasets and applies to light-field data captured by various acquisition methods. Experimental results demonstrate that high-quality NDF can be reconstructed from light-field data using the proposed method. High-resolution disparity can be effectively recovered by NDF, demonstrating its capability for the implicit, continuous representation of scene disparities.

eess.IV↗

arXiv2024

Ray-driven Spectral CT Reconstruction Based on Neural Base-Material Fields

In spectral CT reconstruction, the basis materials decomposition involves solving a large-scale nonlinear system of integral equations, which is highly ill-posed mathematically. This paper proposes a model that parameterizes the attenuation coefficients of the object using a neural field representation, thereby avoiding the complex calculations of pixel-driven projection coefficient matrices during the discretization process of line integrals. It introduces a lightweight discretization method for line integrals based on a ray-driven neural field, enhancing the accuracy of the integral approximation during the discretization process. The basis materials are represented as continuous vector-valued implicit functions to establish a neural field parameterization model for the basis materials. The auto-differentiation framework of deep learning is then used to solve the implicit continuous function of the neural base-material fields. This method is not limited by the spatial resolution of reconstructed images, and the network has compact and regular properties. Experimental validation shows that our method performs exceptionally well in addressing the spectral CT reconstruction. Additionally, it fulfils the requirements for the generation of high-resolution reconstruction images.

eess.IV↗

arXiv2022

Matching entropy based disparity estimation from light field

A major challenge for matching-based depth estimation is to prevent mismatches in occlusion and smooth regions. An effective matching window satisfying three characteristics: texture richness, disparity consistency and anti-occlusion should be able to prevent mismatches to some extent. According to these characteristics, we propose matching entropy in the spatial domain of light field to measure the amount of correct information in a matching window, which provides the criterion for matching window selection. Based on matching entropy regularization, we establish an optimization model for depth estimation with a matching cost fidelity term. To find the optimum, we propose a two-step adaptive matching algorithm. First, the region type is adaptively determined to identify occluding, occluded, smooth and textured regions. Then, the matching entropy criterion is used to adaptively select the size and shape of matching windows, as well as the visible viewpoints. The two-step process can reduce mismatches and redundant calculations by selecting effective matching windows. The experimental results on synthetic and real data show that the proposed method can effectively improve the accuracy of depth estimation in occlusion and smooth regions and has strong robustness for different noise levels. Therefore, high-precision depth estimation from 4D light field data is achieved.

cs.CV↗

arXiv2020

Full Daytime Sub-ambient Radiative Cooling with High Figure of Merit in Commercial-like Paints

Radiative cooling is a passive cooling technology by reflecting sunlight and emitting radiation in the atmospheric sky window. Although highly desired, full daytime sub-ambient radiative cooling in commercial-like single-layer particle-matrix paints is yet to be achieved. In this work, we have demonstrated full daytime sub-ambient radiative cooling in CaCO3-acrylic paint by adopting large bandgap fillers, a high particle concentration and a broad size distribution. Our paint shows the highest solar reflectance of 95.5% among paints and a high sky-window emissivity of 0.94. Field tests show cooling power exceeding 37 W/m2 and lower surface temperature more than 1.7C below ambient at noon. A figure of merit RC is proposed to compare the cooling performance under different weather conditions. The RC of our cooling paint is 0.62, among the best radiative cooling performance while offering unprecedented benefits of the convenient paint form, low cost, and the compatibility with commercial paint fabrication process.

physics.app-ph↗

arXiv2016

On the quantum spin Hall gap of monolayer 1T'-WTe2

Quantum spin Hall (QSH) materials are two-dimensional systems exhibiting insulating bulk and helical edge states simultaneously. A QSH insulator processes topologically non-trivial edge states protected by time-reversal symmetry, so that electrons can propagate unscattered. Realization of such topological phases enables promising applications in spintronics, dissipationless transport and quantum computations. Presently, realization of such QSH-based devices are limited to complicated heterostructures. Monolayer 1T'-WTe2 was predicted to be semimetallic QSH materials, though with a negative band gap. The quasi-particle spectrum obtained using hybrid functional approach shows directly that the quantum spin Hall gap is positive for monolayer 1T'-WTe2. Optical measurement shows a systematic increase in the interband relaxation time with decreasing number of layers, whereas transport measurement reveals Schottcky barrier in ultrathin samples, which is absent for thicker samples. These three independent pieces of evidence indicate that monolayer 1T'-WTe2 is likely a truly 2-dimensional quantum spin Hall insulator.

cond-mat.mtrl-sci↗

arXiv2015

Dynamical Evolution of Anisotropic Response in Black Phosphorus under Ultrafast Photoexcitation

Black phosphorus has recently emerged as a promising material for high performance electronic and optoelectronic device for its high mobility, tunable mid-infrared bandgap and anisotropic electronic properties. Dynamical evolution of photo excited carriers and its induced change of transient electronic properties are critical for materials' high field performance, but remains to be explored for black phosphorus. In this work, we perform angle resolved transient reflection spectroscopy to study the dynamical evolution of anisotropic properties of black phosphorus under photo excitation. We find that the anisotropy of reflectivity is enhanced in the pump induced quasi-equilibrium state, suggesting an extraordinary enhancement of the anisotropy in dynamical conductivity in hot carrier dominated regime. These results raise enormous possibilities of creating high field, angle sensitive electronic, optoelectronic and remote sensing devices exploiting the dynamical electronic anisotropic with black phosphorus.

cond-mat.mtrl-sci↗

arXiv2014

Ultrafast Terahertz Probe of Transient Evolution of Charged and Neutral Phase of Photoexcited Electron-hole Gas in Monolayer Semiconductor

We investigate the dynamical formation of excitons from photoexcited electron-hole plasma and its subsequent decay dynamics in monolayer MoS2 grown by chemical vapor deposition using ultrafast pump and terahertz probe spectroscopy. Different photoexcited electron-hole states are resolved based on their distinct responses to THz photon and decay lifetime. The observed transient THz transmission can be fit with two decay components: a fast component with decay lifetime of 20 ps, which is attributed to exciton life time including the exciton formation and subsequent intraexciton relaxation; a slow component with extremely long decay lifetime of several ns due to either localized exciton state or a long live dark exciton state which is uncovered for the first time. The relaxation dynamics is further verified by temperature and pump fluence dependent studies of the decay time constants.

cond-mat.mtrl-sci↗

arXiv2013

Valley Carrier Dynamics in Monolayer Molybdenum Disulphide from Helicity Resolved Ultrafast Pump-probe Spectroscopy

We investigate the valley related carrier dynamics in monolayer MoS2 using helicity resolved non-degenerate ultrafast pump-probe spectroscopy at the vicinity of the high-symmetry K point under the temperature down to 78 K. Monolayer MoS2 shows remarkable transient reflection signals, in stark contrast to bilayer and bulk MoS2 due to the enhancement of many-body effect at reduced dimensionality. The helicity resolved ultrafast time-resolved result shows that the valley polarization is preserved for only several ps before scattering process makes it undistinguishable. We suggest that the dynamical degradation of valley polarization is attributable primarily to the exciton trapping by defect states in the exfoliated MoS2 samples. Our experiment and a tight-binding model analysis also show that the perfect valley CD selectivity is fairly robust against disorder at the K point, but quickly decays from the high-symmetry point in the momentum space in the presence of disorder.

physics.optics↗