arXiv subjects

Shaohui Zhang

Publications and source records attributed to Shaohui Zhang.

At least 19 recordsLinked to original sources

arXiv2026

ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstruction

Autonomous high-fidelity object reconstruction is fundamental for creating digital assets and bridging the simulation-to-reality gap in robotics. We present ObjSplat, an active reconstruction framework that leverages Gaussian surfels as a unified representation to progressively reconstruct unknown objects with both photorealistic appearance and accurate geometry. Addressing the limitations of conventional opacity or depth-based cues, we introduce a geometry-aware viewpoint evaluation pipeline that explicitly models back-face visibility and occlusion-aware multi-view covisibility, reliably identifying under-reconstructed regions even on geometrically complex objects. Furthermore, to overcome the limitations of greedy planning strategies, ObjSplat employs a next-best-path (NBP) planner that performs multi-step lookahead on a dynamically constructed spatial graph. By jointly optimizing information gain and movement cost, this planner generates globally efficient trajectories. Extensive experiments in simulation and on real-world cultural artifacts demonstrate that ObjSplat produces physically consistent models within minutes, achieving superior reconstruction fidelity and surface completeness while significantly reducing scan time and path length compared to state-of-the-art approaches. Project page: https://li-yuetao.github.io/ObjSplat-page/ .

cs.RO↗

arXiv2025

Advancing Tumor Budding Detection with Fourier Ptychography Microscopy

Background: Tumour budding is an independent predictor of metastasis and prognosis in colorectal cancer and is a vital part of the pathology specification report. In a conventional pathological section observation process, pathologists have to repeatedly switch from 10x objective to 20x objective several times to localize and image the target region. Besides the switching operations, repeated manual or electro-mechanical focusing is also very time-consuming, affecting the total time for pathological diagnosis. In addition, It is usually necessary to remove the manually marked symbols on the stained pathology slides used for classification and management before observation. Methods: In this paper, we utilize Fourier ptychographic microscopy (FPM) in the pathological diagnosis process to realize large space-bandwidth product imaging, quantitative phase imaging, and digital refocusing in the observation process without any mechanical operations, which can therefore simplify the above-mentioned cumbersome diagnostic processes. We first verify the effectiveness and efficiency of the proposed method with several typical pathological sections. Then, instead of manually erasing, we also prove that FP framework can digitally remove the artificial markers with its digital refocusing ability. Results: At last, we demonstrated pathologists can achieve 100% diagnostic accuracy with FPM imaging results. Conclusions: The proposed method can greatly simplify the process of pathological diagnosis, and the related addon hardware system does not require expensive components, which makes it have great potential for promotion in the field of pathological diagnosis.

physics.med-ph↗

arXiv2025

Differentiable Imaging Meets Adaptive Neural Dropout: An Advancing Method for Transparent Object Tomography

Label-free tomographic microscopy offers a compelling means to visualize three-dimensional (3D) refractive index (RI) distributions from two-dimensional (2D) intensity measurements. However, limited forward-model accuracy and the ill-posed nature of the inverse problem hamper artifact-free reconstructions. Meanwhile, artificial neural networks excel at modeling nonlinearities. Here, we employ a Differentiable Imaging framework that represents the 3D sample as a multi-layer neural network embedding physical constraints of light propagation. Building on this formulation, we propose a physics-guided Adaptive Dropout Neural Network (ADNN) for optical diffraction tomography (ODT), focusing on network topology and voxel-wise RI fidelity rather than solely on input-output mappings. By exploiting prior knowledge of the sample's RI, the ADNN adaptively drops and reactivates neurons, enhancing reconstruction accuracy and stability. We validate this method with extensive simulations and experiments on weakly and multiple-scattering samples under different imaging setups. The ADNN significantly improves quantitative 3D RI reconstructions, providing superior optical-sectioning and effectively suppressing artifacts. Experimental results show that the ADNN reduces the Mean Absolute Error (MAE) by a factor of 3 to 5 and increases the Structural Similarity Index Metric (SSIM) by about 4 to 30 times compared to the state-of-the-art approach.

physics.optics↗

arXiv2025

CAR-LOAM: Color-Assisted Robust LiDAR Odometry and Mapping

In this letter, we propose a color-assisted robust framework for accurate LiDAR odometry and mapping (LOAM). Simultaneously receiving data from both the LiDAR and the camera, the framework utilizes the color information from the camera images to colorize the LiDAR point clouds and then performs iterative pose optimization. For each LiDAR scan, the edge and planar features are extracted and colored using the corresponding image and then matched to a global map. Specifically, we adopt a perceptually uniform color difference weighting strategy to exclude color correspondence outliers and a robust error metric based on the Welsch's function to mitigate the impact of positional correspondence outliers during the pose optimization process. As a result, the system achieves accurate localization and reconstructs dense, accurate, colored and three-dimensional (3D) maps of the environment. Thorough experiments with challenging scenarios, including complex forests and a campus, show that our method provides higher robustness and accuracy compared with current state-of-the-art methods.

cs.RO↗

arXiv2025

PB-NBV: Efficient Projection-Based Next-Best-View Planning Framework for Reconstruction of Unknown Objects

Completely capturing the three-dimensional (3D) data of an object is essential in industrial and robotic applications. The task of next-best-view (NBV) planning is to calculate the next optimal viewpoint based on the current data, gradually achieving a complete 3D reconstruction of the object. However, many existing NBV planning algorithms incur heavy computational costs due to the extensive use of ray-casting. Specifically, this framework refits different types of voxel clusters into ellipsoids based on the voxel structure. Then, the next optimal viewpoint is selected from the candidate views using a projection-based viewpoint quality evaluation function in conjunction with a global partitioning strategy. This process replaces extensive ray-casting, significantly improving the computational efficiency. Comparison experiments in the simulation environment show that our framework achieves the highest point cloud coverage with low computational time compared to other frameworks. The real-world experiments also confirm the efficiency and feasibility of the framework. Our method will be made open source to benefit the community.

cs.RO↗

arXiv2024

High-space-bandwidth product characterization of metalenses with Fourier ptychographic microscopy

Large numerical aperture (NA) and large aperture metalenses have shown significant performance and abundant applications in biomedical and astronomical imaging fields. However, the high space-bandwidth product (SBP) requirements for measuring the phase of these metalenses, characterized by small phase periods and large apertures, have resulted in no effective techniques for sufficient characterization. In this paper, we propose a high SBP phase characterization technique using Fourier ptychographic microscopy (FPM), enabling a high spatial resolution and wide field of view simultaneously. To demonstrate the feasibility and effectiveness of this technique, we achieve a high SBP (4.91 megapixels) measurement and characterization for focusing and focusing vortex metalenses, quantitatively displaying the effect of fabrication error on their typical optical performance. Furthermore, we characterize the aberration type and amount of wavefront deviations caused by fabrication. We also analyze compensation methods for different aberrations based on the wavefront characterization results, providing a targeted alignment strategy for optimizing overall optical system performance. We believe that our high SBP characterization technique cannot only help to improve metalens design but also optimize its fabrication processing, which will pave the way for the diversified applications of metalenses.

physics.optics↗

arXiv2024

ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splatting

We propose ActiveSplat, an autonomous high-fidelity reconstruction system leveraging Gaussian splatting. Taking advantage of efficient and realistic rendering, the system establishes a unified framework for online mapping, viewpoint selection, and path planning. The key to ActiveSplat is a hybrid map representation that integrates both dense information about the environment and a sparse abstraction of the workspace. Therefore, the system leverages sparse topology for efficient viewpoint sampling and path planning, while exploiting view-dependent dense prediction for viewpoint selection, facilitating efficient decision-making with promising accuracy and completeness. A hierarchical planning strategy based on the topological map is adopted to mitigate repetitive trajectories and improve local granularity given limited time budgets, ensuring high-fidelity reconstruction with photorealistic view synthesis. Extensive experiments and ablation studies validate the efficacy of the proposed method in terms of reconstruction accuracy, data coverage, and exploration efficiency. The released code will be available on our project page: https://li-yuetao.github.io/ActiveSplat/.

cs.RO↗

arXiv2024

An Efficient Projection-Based Next-best-view Planning Framework for Reconstruction of Unknown Objects

Efficiently and completely capturing the three-dimensional data of an object is a fundamental problem in industrial and robotic applications. The task of next-best-view (NBV) planning is to infer the pose of the next viewpoint based on the current data, and gradually realize the complete three-dimensional reconstruction. Many existing algorithms, however, suffer a large computational burden due to the use of ray-casting. To address this, this paper proposes a projection-based NBV planning framework. It can select the next best view at an extremely fast speed while ensuring the complete scanning of the object. Specifically, this framework refits different types of voxel clusters into ellipsoids based on the voxel structure.Then, the next best view is selected from the candidate views using a projection-based viewpoint quality evaluation function in conjunction with a global partitioning strategy. This process replaces the ray-casting in voxel structures, significantly improving the computational efficiency. Comparative experiments with other algorithms in a simulation environment show that the framework proposed in this paper can achieve 10 times efficiency improvement on the basis of capturing roughly the same coverage. The real-world experimental results also prove the efficiency and feasibility of the framework.

cs.RO↗

arXiv2024

Batch-FPM: Random batch-update multi-parameter physical Fourier ptychography neural network

Fourier Ptychographic Microscopy (FPM) is a computational imaging technique that enables high-resolution imaging over a large field of view. However, its application in the biomedical field has been limited due to the long image reconstruction time and poor noise robustness. In this paper, we propose a fast and robust FPM reconstruction method based on physical neural networks with batch update stochastic gradient descent (SGD) optimization strategy, capable of achieving attractive results with low single-to-noise ratio and correcting multiple system parameters simultaneously. Our method leverages a random batch optimization approach, breaks away from the fixed sequential iterative order and gives greater attention to high-frequency information. The proposed method has better convergence performance even for low signal-to-noise ratio data sets, such as low exposure time dark-field images. As a result, it can greatly increase the image recording and result reconstruction speed without any additional hardware modifications. By utilizing advanced deep learning optimizers and perform parallel computational scheme, our method enhances GPU computational efficiency, significantly reducing reconstruction costs. Experimental results demonstrate that our method achieves near real-time digital refocusing of a 1024 x 1024 pixels region of interest on consumer-grade GPUs. This approach significantly improves temporal resolution (by reducing the exposure time of dark-field images), noise resistance, and reconstruction speed, and therefore can efficiently promote the practical application of FPM in clinical diagnostics, digital pathology, and biomedical research, etc. In addition, we believe our algorithm scheme can help researchers quickly validate and implement FPM-related ideas. We invite requests for the full code via email.

eess.IV↗

arXiv2024

Hybrid deep learning and physics-based neural network for programmable illumination computational microscopy

Relying on either deep models or physical models are two mainstream approaches for solving inverse sample reconstruction problems in programmable illumination computational microscopy. Solutions based on physical models possess strong generalization capabilities while struggling with global optimization of inverse problems due to a lack of insufficient physical constraints. In contrast, deep learning methods have strong problem-solving abilities, but their generalization ability is often questioned because of the unclear physical principles. Besides, conventional deep models are difficult to apply to some specific scenes because of the difficulty in acquiring high-quality training data and their limited capacity to generalize across different scenarios. In this paper, to combine the advantages of deep models and physical models together, we propose a hybrid framework consisting of three sub-neural networks (two deep learning networks and one physics-based network). We first obtain a result with rich semantic information through a light deep learning neural network and then use it as the initial value of the physical network to make its output comply with physical process constraints. These two results are then used as the input of a fusion deep learning neural work which utilizes the paired features between the reconstruction results of two different models to further enhance imaging quality. The final result integrates the advantages of both deep models and physical models and can quickly solve the computational reconstruction inverse problem in programmable illumination computational microscopy and achieve better results. We verified the feasibility and effectiveness of the proposed hybrid framework with theoretical analysis and actual experiments on resolution targets and biological samples.

eess.IV↗

arXiv2023

Refractive index tomography with a physics based optical neural network

The non-interference three-dimensional refractive index(RI) tomography has attracted extensive attention in the life science field for its simple system implementation and robust imaging performance. However, the complexity inherent in the physical propagation process poses significant challenges when the sample under study deviates from the weak scattering approximation. Such conditions complicate the task of achieving global optimization with conventional algorithms, rendering the reconstruction process both time-consuming and potentially ineffective. To address such limitations, this paper proposes an untrained multi-slice neural network(MSNN) with an optical structure, in which each layer has a clear corresponding physical meaning according to the beam propagation model. The network does not require pre-training and performs good generalization and can be recovered through the optimization of a set of intensity images. Concurrently, MSNN can calibrate the intensity of different illumination by learnable parameters, and the multiple backscattering effects have also been taken into consideration by integrating a "scattering attenuation layer" between adjacent "refractive index" layers in the MSNN. Both simulations and experiments have been conducted carefully to demonstrate the effectiveness and feasibility of the proposed method. Experimental results reveal that MSNN can enhance clarity with increased efficiency in RI tomography. The implementation of MSNN introduces a novel paradigm for RI tomography.

physics.optics↗

arXiv2023

Adaptive coded illumination Fourier ptychography microscopy based on physical neural network

Fourier Ptychographic Microscopy (FPM) is a computational technique that achieves a large space-bandwidth product imaging. It addresses the challenge of balancing a large field of view and high resolution by fusing information from multiple images taken with varying illumination angles. Nevertheless, conventional FPM framework always suffers from long acquisition time and a heavy computational burden. In this paper, we propose a novel physical neural network that generates an adaptive illumination mode by incorporating temporally-encoded illumination modes as a distinct layer, aiming to improve the acquisition and calculation efficiency. Both simulations and experiments have been conducted to validate the feasibility and effectiveness of the proposed method. It is worth mentioning that, unlike previous works that obtain the intensity of a multiplexed illumination by post-combination of each sequentially illuminated and obtained low-resolution images, our experimental data is captured directly by turning on multiple LEDs with a coded illumination pattern. Our method has exhibited state-of-the-art performance in terms of both detail fidelity and imaging velocity when assessed through a multitude of evaluative aspects.

physics.optics↗

arXiv2023

Single-shot quantitative differential phase contrast imaging combined with programmable polarization multiplexing illumination

We propose a single-shot quantitative differential phase contrast (DPC) method with polarization multiplexing illumination. In the illumination module of our system, the programmable LED array is divided into four quadrants and covered with polarizing films of four different polarization angles. We use a polarization camera with polarizers before the pixels in the imaging module. By matching the polarization angle between the polarizing films over the custom LED array and the polarizers in the camera, two sets of asymmetric illumination acquisition images can be calculated from a single-shot acquisition image. Combined with the phase transfer function, we can calculate the quantitative phase of the sample. We present the design, implementation, and experimental image data demonstrating the ability of our method to obtain quantitative phase images of the phase resolution target, as well as Hela cells.

physics.optics↗

arXiv2022

Robust full-pose-parameter estimation for the LED array in Fourier ptychographic microscopy

Fourier ptychographic microscopy (FPM) can achieve quantitative phase imaging with a large space-bandwidth product by synthesizing a set of low-resolution intensity images captured under angularly varying illuminations. Determining accurate illumination angles is critical because the consistency between actual systematic parameters and those used in the recovery algorithm is essential for high-quality imaging. This paper presents a full-pose-parameter and physics-based method for calibrating illumination angles. Using a physics-based model constructed with general knowledge of the employed microscope and the brightfield-to-darkfield boundaries inside captured images, we can solve for the full-pose parameters of misplaced LED array, which consist of the distance between the sample and the LED array, two orthogonal lateral shifts, one in-plane rotation angle, and two tilt angles, to correct illumination angles precisely. The feasibility and effectiveness of the proposed method for recovering random or remarkable pose parameters have been demonstrated by both qualitative and quantitative experiments. Due to the completeness of the pose parameters, the clarity of the physical model, and the high robustness for arbitrary misalignments, our method can significantly facilitate the design, implementation, and application of concise and robust FPM platforms.

physics.optics↗

arXiv2022

Pose correction scheme for camera-scanning Fourier ptychography based on camera calibration and homography transform

Fourier ptychography (FP), as a computational imaging method, is a powerful tool to improve imaging resolution. Camera-scanning Fourier ptychography extends the application of FP from micro to macro creatively. Due to the non-ideal scanning of the camera driven by the mechanical translation stage, the pose error of the camera occurs, greatly degrading the reconstruction quality, while a precise translation stage is expensive and not suitable for wide-range imaging. Here, to improve the imaging performance of camera-scanning Fourier ptychography, we propose a pose correction scheme based on camera calibration and homography transform approaches. The scheme realizes the accurate alignment of data set and location error correction in the frequency domain. Simulation and experimental results demonstrate this method can optimize the reconstruction results and realize high-quality imaging effectively. Combined with the feature recognition algorithm, the scheme provides the possibility for applying FP in remote sensing imaging and space imaging.

eess.IV↗

arXiv2022

Parallel Fourier Ptychography reconstruction

Fourier ptychography has attracted a wide range of focus for its ability of large space-bandwidth-produce, and quantative phase measurement. It is a typical computational imaging technique which refers to optimizing both the imaging hardware and reconstruction algorithms simultaneously. The data redundancy and inverse problem algorithms are the sources of FPM's excellent performance. But at the same time, this large amount of data processing and complex algorithms also greatly reduce the imaging speed. In this article, we propose a parallel Fourier ptychography reconstruction framework consisting of three levels of parallel computing parts and implemented it with both central processing unit (CPU) and compute unified device architecture (CUDA) platform. In the conventional FPM reconstruction framework, the sample image is divided into multiple sub-regions for separately processing because the illumination angles for different subregions are varied for the same LED and different subregions contain different defocus distances due to the non-planar distribution or non-ideal posture of biological sample. We first build a parallel computing sub-framework in spatial domain based on the above-mentioned characteristics. And then, by utilizing the sequential characteristics of different spectrum regions to update, a parallel computing sub-framework in the spectrum domain is carried out in our scheme. The feasibility of the proposed parallel FPM reconstruction framework is verified with different experimental results acquired with the system we built.

eess.IV↗

arXiv2022

Fourier ptychography multi-parameter neural network with composite physical priori optimization

Fourier ptychography microscopy(FP) is a recently developed computational imaging approach for microscopic super-resolution imaging. By turning on each light-emitting-diode (LED) located on different position on the LED array sequentially and acquiring the corresponding images that contain different spatial frequency components, high spatial resolution and quantitative phase imaging can be achieved in the case of large field-of-view. Nevertheless, FPM has high requirements for the system construction and data acquisition processes, such as precise LEDs position, accurate focusing and appropriate exposure time, which brings many limitations to its practical applications. In this paper, inspired by artificial neural network, we propose a Fourier ptychography multi-parameter neural network (FPMN) with composite physical prior optimization. A hybrid parameter determination strategy combining physical imaging model and data-driven network training is proposed to recover the multi layers of the network corresponding to different physical parameters, including sample complex function, system pupil function, defocus distance, LED array position deviation and illumination intensity fluctuation, etc. Among these parameters, LED array position deviation is recovered based on the features of brightfield to darkfield transition low-resolution images while the others are recovered in the process of training of the neural network. The feasibility and effectiveness of FPMN are verified through simulations and actual experiments. Therefore FPMN can evidently reduce the requirement for practical applications of FPM.

physics.optics↗

arXiv2021

Robust Fourier ptychographic microscopy via a physics-based defocusing strategy for calibrating angle-varied LED illumination

Fourier ptychographic microscopy (FPM) is a recently developed computational imaging technique for wide-field, high-resolution microscopy with a high space-bandwidth product. It integrates the concepts of synthetic aperture and phase retrieval to surpass the resolution limit imposed by the employed objective lens. In the FPM framework, the position of each sub-spectrum needs to be accurately known to ensure the success of the phase retrieval process. Different from the conventional methods with mechanical adjustment or data-driven optimization strategies, here we report a physics-based defocusing strategy for correcting large-scale positional deviation of the LED illumination in FPM. Based on a subpixel image registration process with a defocused object, we can directly infer the illumination parameters including the lateral offsets of the light source, the in-plane rotation angle of the LED array, and the distance between the sample and the LED board. The feasibility and effectiveness of our method are validated with both simulation study and experiments. We show that the reported strategy can obtain high-quality reconstruction of both the complex object and pupil even the LED array is randomly placed under the sample with both unknown lateral offsets and rotations. As such, it enables the development of robust FPM systems by reducing the requirement on fine mechanical adjustment and data-driven correction in the construction process.

physics.optics↗