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

Fourier ptychography microscopy(FPM) 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.

Deep learning has been proven to provide solutions for computational ghost imaging (CGI). However, in current CGI techniques, the quality of the reconstructed image is adversely affected by the position and intensity of the scattering medium. In this study, the feasibility of using a deep neural network (DNN) by using the hybrid simulated data to facilitate CGI through a scattering medium is demonstrated, particularly when the scattering medium is in front of an object. Under a specific order of the measurement matrix, the CGI measurement equation is introduced along with a disturbance factor of the scattering effect to generate simulation data, thereby representing imaging situations with the scattering medium at different positions. The selection of disturbance parameters is determined by the correlation between the simulation signal and the experimental signal. Then an end-to-end DNN is trained using experimentally obtained light intensity signals, and it shows that the quality of the reconstruction results is improved when there is a scattering medium in the emission path. The reported technique effectively solves the problem of CGI reconstruction under different scattering paths with a common DNN, and may have broad applications in fast adaptive CGI for new and uncertain scenarios.

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 simulations and experiments. We show that the reported strategy can obtain high-quality reconstructions of both the complex object and pupil function 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 requirements on fine mechanical adjustment and data-driven correction in the construction process.

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.

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.