Zhu Huixin

Dr. Zhu Huixin


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 November 2024 in Artificial Intelligence Review
Verified
Journal Article
Open access
PDF file
Zhu HuixinZhu Huixin
Zhu Huixin
ZZZhili Zhang
Zhili Zhang
ZJZhao JunYang
Zhao JunYang
HDHui Duan
Hui Duan
YDYao Ding
Yao Ding
JYJunsong Yuan
Junsong Yuan
As the latest research result of the explicit radiated field technology, 3D Gaussian Splatting (3D GS) replaces the implicit expression represented by Neural Radiated Field (NeRF) and has become the hottest research direction in 3D scene reconstruction. Given the innovative work and vigorous development of 3D GS in autonomous driving, this paper comprehensively reviews and summarizes the existing related research to showcase the evolution of the 3D GS technology and possible future development directions. First, the overall research background of 3D GS is introduced based on two aspects 3D scene reconstruction methods and 3D GS research progress. Second, the relevant knowledge points of 3D GS and the core formulas to clarify the mathematical mechanism of 3D GS are presented. Third, the primary applications of the 3D scene reconstruction technology based on 3D GS in automatic driving are presented through new perspective synthesis, scene understanding, and simultaneous localization and map building (SLAM). Finally, the research frontier directions of 3D GS in autonomous driving are described, including structure optimization, 4D scene reconstruction, and cross-domain research. This paper may provide an effective and convenient pathway for researchers to understand, explore, apply this novel research method, and promote the development and application of 3D GS in automatic driving.

17 November 2025 in Fractal and Fractional
Verified
Journal Article
Open access
PDF file
JZJunyang Zhao
Junyang Zhao
Zhu HuixinZhu Huixin
Zhu Huixin
ZZZhili Zhang
Zhili Zhang
Mingtao FengMingtao Feng
Mingtao Feng
HYHan Yu
Han Yu
YLYuxuan Li
Yuxuan Li
In dense visual simultaneous localization and mapping VSLAM (VSLAM), a fundamental challenge lies in the inability of existing loss functions to dynamically balance luminance, contrast, and structural fidelity under photometric variations, while their underlying mechanisms, particularly the conventional Gaussian kernel in SSIM, suffer from limited receptive fields due to rapid exponential decay, preventing the capture of long-range dependencies essential for global consistency. To address this, we propose a fractional Gaussian field (FGF) that synergizes Caputo derivatives with Gaussian weighting, creating a hybrid kernel that couples power-law decay for long-range memory with local smoothness. This foundational kernel serves as the core component of FGF-SSIM, a novel loss function that adaptively recalibrates luminance, contrast, and structure using fractional-order statistics. The proposed FGF-SSIM is further integrated into a complete 3D Gaussian Splatting (3DGS)-based SLAM system, named FGF-SLAM, where it is employed across both tracking and mapping modules to enhance performance. Extensive evaluations demonstrate state-of-the-art performance across multiple benchmarks. Comprehensive analysis confirms the superior long-range dependency of the fractional kernel, dedicated illumination robustness tests validate the enhanced invariance of FGF-SSIM, and quantitative results on TUM and Replica datasets show significant improvements in reconstruction quality and trajectory estimation. Ablation studies further substantiate the contribution of each proposed component.

4 October 2025 in Sensors
Verified
Journal Article
Open access
PDF file
ZJZhao JunYang
Zhao JunYang
SLShenHua 中国大陆 Lv
ShenHua 中国大陆 Lv
Zhu HuixinZhu Huixin
Zhu Huixin
YLYaru Li
Yaru Li
HYHan Yu
Han Yu
Kefan ZhangKefan Zhang
Kefan Zhang
To address the ill-posedness of the Hessian matrix in monocular visual-inertial SLAM (Simultaneous Localization and Mapping) caused by unobservable depth of feature points, which leads to convergence difficulties and reduced robustness, this paper proposes a Pre-Dog-Leg feature optimization method based on an adaptive preconditioner. First, we propose a multi-candidate initialization method with robust characteristics. This method effectively circumvents erroneous depth initialization by introducing multiple depth assumptions and geometric consistency constraints. Second, we address the pathology of the Hessian matrix of the feature points by constructing a hybrid SPAI-Jacobi adaptive preconditioner. This preconditioner is capable of identifying matrix pathology and dynamically enabling preconditioning as a strategy. Finally, we construct a hybrid adaptive preconditioner for the traditional Dog-Leg numerical optimization method. To address the issue of degraded convergence performance when solving pathological problems, we map the pathological optimization problem from the original parameter space to a well-conditioned preconditioned space. The optimization equivalence is maintained by variable recovery. The experiments on the EuRoC dataset show that the method reduces the number of Hessian matrix conditionals by a factor of 7.9, effectively suppresses outliers, and significantly improves the overall convergence time. From the analysis of trajectory error, the absolute trajectory error is reduced by up to 16.48% relative to RVIO2 on the MH_01 sequence, 20.83% relative to VINS-mono on the MH_02 sequence, and up to 14.73% relative to VINS-mono and 34.0% relative to OpenVINS on the highly dynamic MH_05 sequence, indicating that the algorithm achieves higher localization accuracy and stronger system robustness.

10 May 2026 in Sensors
Verified
Journal Article
Open access
PDF file
ZJZhao JunYang
Zhao JunYang
HYHan Yu
Han Yu
ZZZhili Zhang
Zhili Zhang
YLYaru Li
Yaru Li
Zhu HuixinZhu Huixin
Zhu Huixin
JWJiayi Wang
Jiayi Wang
To address the issues of insufficient robustness, large depth recovery errors, and poor scene adaptability currently present in the initialisation phase of event-based stereo visual inertial SLAM systems, we propose a global BA initialisation method based on an adaptive threshold robust kernel function, ES-ATRK. The algorithm first achieves spatio-temporal fusion of events and visual features. Event features are triangulated to obtain depth values that serve as the 3D map, whilst visual features provide 2D observations; both modalities jointly feed the Structure from Motion (SfM) pipeline, laying the foundation for global bundle adjustment (BA) optimisation. The core contribution lies in incorporating a robust kernel function into the global BA to suppress outlier interference and in designing an adaptive thresholding algorithm that dynamically determines the kernel threshold. Furthermore, the algorithm calculates an initial threshold based on the quantile distribution of residuals prior to BA optimisation, combined with validity checks and a multi-round iterative smoothing adjustment strategy, thereby achieving scene-adaptive thresholding. In over 85% of the test scenes on the VECtor dataset, its localisation accuracy improved by at least 10% compared to existing mainstream event-based SLAM methods, such as ESVIO and USLAM. In high-dynamic scenes, its ATE performance is approximately twice that of mainstream models such as ESIO, and it maintains excellent positioning accuracy and stability of three-axis errors in generalisation tests on the HKU and MVSEC datasets. Furthermore, in the large-scale outdoor testing scenarios of the DSEC dataset, ES-ATRK also demonstrates superior feature tracking and trajectory estimation performance. This method effectively enhances the robustness of initialisation and depth recovery performance in event-based stereo visual inertial SLAM systems, reduces overall positioning error, and offers greater adaptability in challenging scenarios such as low-texture, high-dynamic, and HDR environments.

6 June 2026 in Array
Verified
Journal Article
Open access
Zhu HuixinZhu Huixin
Zhu Huixin
JZJunyang Zhao
Junyang Zhao
YWYutie Wang
Yutie Wang
CXChen Xie
Chen Xie
FZFan Zhang
Fan Zhang
JWJiayi Wang
Jiayi Wang

6 September 2026 in Drones
Verified
Journal Article
Open access
PDF file
JZJunyang Zhao
Junyang Zhao
YHYu Han
Yu Han
ZZZhili Zhang
Zhili Zhang
YLYaru Li
Yaru Li
Zhu HuixinZhu Huixin
Zhu Huixin
JWJiayi Wang
Jiayi Wang
Unmanned aerial vehicles (UAVs) have become essential platforms for remote sensing in challenging environments such as high-dynamic-range (HDR) scenes and low-texture areas. However, conventional frame-based visual–inertial simultaneous localization and mapping (SLAM) systems often suffer from motion blur and overexposure during high-speed UAV flight, leading to state estimation failure. To address numerical instability in marginalization, weak scene adaptability, and insufficient outlier suppression in event-based stereo visual–inertial SLAM systems for aerial applications, we propose HESVI, a hybrid marginalization and adaptive heterogeneous kernel state estimation method for UAV remote sensing. Our method first establishes a focal-length-driven cross-modal inverse depth consistency constraint to couple image and event inverse depths, providing high-quality priors for optimization. Such lightweight prior generation is designed with the limited onboard computing resources of UAV platforms in mind. A hybrid marginalization strategy is then introduced, employing block-parallel tall–skinny QR (TSQR) acceleration based on Householder reflections alongside dynamic Tikhonov regularization and first-estimates Jacobian (FEJ) linearization to balance computational efficiency and numerical stability. Furthermore, an adaptive heterogeneous Cauchy kernel maps differentiated thresholds to image and event features according to their average effective tracking lengths, enabling dynamic outlier suppression. Experiments on the VECtor, MVSEC, and HKU datasets demonstrate that HESVI achieves the best absolute trajectory error (ATE) on the vast majority of the evaluated sequences, with average ATE reductions of 47.2%, 41.2%, and 26.8% over PL-EVIO, ESIO, and ESVIO, where each average is computed only over the sequences on which the corresponding baseline runs successfully. The method also exhibits excellent performance in complex remote-sensing scenarios and generalization tests. HESVI effectively enhances the numerical stability, scene adaptability, and localization accuracy of event-based stereo visual–inertial SLAM systems in challenging UAV remote-sensing environments.