Wide-Field, High-Resolution Reconstruction in Computational Multi-Aperture Miniscope Using a Fourier Neural Network

Traditional fluorescence microscopy is constrained by inherent trade-offs among resolution, field-of-view, and system complexity. To navigate these challenges, we introduce a simple and low-cost computational multi-aperture miniature microscope, utilizing a microlens array for single-shot wide-field, high-resolution imaging. Addressing the challenges posed by extensive view multiplexing and non-local, shift-variant aberrations in this device, we present SV-FourierNet, a novel multi-channel Fourier neural network. SV-FourierNet facilitates high-resolution image reconstruction across the entire imaging field through its learned global receptive field. We establish a close relationship between the physical spatially-varying point-spread functions and the network's learned effective receptive field. This ensures that SV-FourierNet has effectively encapsulated the spatially-varying aberrations in our system, and learned a physically meaningful function for image reconstruction. Training of SV-FourierNet is conducted entirely on a physics-based simulator. We showcase wide-field, high-resolution video reconstructions on colonies of freely moving C. elegans and imaging of a mouse brain section. Our computational multi-aperture miniature microscope, augmented with SV-FourierNet, represents a major advancement in computational microscopy and may find broad applications in biomedical research and other fields requiring compact microscopy solutions.

UniVG: Towards UNIfied-modal Video Generation

Diffusion based video generation has received extensive attention and achieved considerable success within both the academic and industrial communities. However, current efforts are mainly concentrated on single-objective or single-task video generation, such as generation driven by text, by image, or by a combination of text and image. This cannot fully meet the needs of real-world application scenarios, as users are likely to input images and text conditions in a flexible manner, either individually or in combination. To address this, we propose a Unified-modal Video Genearation system that is capable of handling multiple video generation tasks across text and image modalities. To this end, we revisit the various video generation tasks within our system from the perspective of generative freedom, and classify them into high-freedom and low-freedom video generation categories. For high-freedom video generation, we employ Multi-condition Cross Attention to generate videos that align with the semantics of the input images or text. For low-freedom video generation, we introduce Biased Gaussian Noise to replace the pure random Gaussian Noise, which helps to better preserve the content of the input conditions. Our method achieves the lowest Fr\'echet Video Distance (FVD) on the public academic benchmark MSR-VTT, surpasses the current open-source methods in human evaluations, and is on par with the current close-source method Gen2. For more samples, visit https://univg-baidu.github.io.

HiCAST: Highly Customized Arbitrary Style Transfer with Adapter Enhanced Diffusion Models

The goal of Arbitrary Style Transfer (AST) is injecting the artistic features of a style reference into a given image/video. Existing methods usually focus on pursuing the balance between style and content, whereas ignoring the significant demand for flexible and customized stylization results and thereby limiting their practical application. To address this critical issue, a novel AST approach namely HiCAST is proposed, which is capable of explicitly customizing the stylization results according to various source of semantic clues. In the specific, our model is constructed based on Latent Diffusion Model (LDM) and elaborately designed to absorb content and style instance as conditions of LDM. It is characterized by introducing of \textit{Style Adapter}, which allows user to flexibly manipulate the output results by aligning multi-level style information and intrinsic knowledge in LDM. Lastly, we further extend our model to perform video AST. A novel learning objective is leveraged for video diffusion model training, which significantly improve cross-frame temporal consistency in the premise of maintaining stylization strength. Qualitative and quantitative comparisons as well as comprehensive user studies demonstrate that our HiCAST outperforms the existing SoTA methods in generating visually plausible stylization results.

MixTEA: Semi-supervised Entity Alignment with Mixture Teaching

Semi-supervised entity alignment (EA) is a practical and challenging task because of the lack of adequate labeled mappings as training data. Most works address this problem by generating pseudo mappings for unlabeled entities. However, they either suffer from the erroneous (noisy) pseudo mappings or largely ignore the uncertainty of pseudo mappings. In this paper, we propose a novel semi-supervised EA method, termed as MixTEA, which guides the model learning with an end-to-end mixture teaching of manually labeled mappings and probabilistic pseudo mappings. We firstly train a student model using few labeled mappings as standard. More importantly, in pseudo mapping learning, we propose a bi-directional voting (BDV) strategy that fuses the alignment decisions in different directions to estimate the uncertainty via the joint matching confidence score. Meanwhile, we also design a matching diversity-based rectification (MDR) module to adjust the pseudo mapping learning, thus reducing the negative influence of noisy mappings. Extensive results on benchmark datasets as well as further analyses demonstrate the superiority and the effectiveness of our proposed method.

EventLFM: Event Camera integrated Fourier Light Field Microscopy for Ultrafast 3D imaging

Ultrafast 3D imaging is indispensable for visualizing complex and dynamic biological processes. Conventional scanning-based techniques necessitate an inherent tradeoff between the acquisition speed and space-bandwidth product (SBP). While single-shot 3D wide-field techniques have emerged as an attractive solution, they are still bottlenecked by the synchronous readout constraints of conventional CMOS architectures, thereby limiting the data throughput by frame rate to maintain a high SBP. Here, we present EventLFM, a straightforward and cost-effective system that circumnavigates these challenges by integrating an event camera with Fourier light field microscopy (LFM), a single-shot 3D wide-field imaging technique. The event camera operates on a novel asynchronous readout architecture, thereby bypassing the frame rate limitations intrinsic to conventional CMOS systems. We further develop a simple and robust event-driven LFM reconstruction algorithm that can reliably reconstruct 3D dynamics from the unique spatiotemporal measurements from EventLFM. We experimentally demonstrate that EventLFM can robustly image fast-moving and rapidly blinking 3D samples at KHz frame rates and furthermore, showcase EventLFM's ability to achieve 3D tracking of GFP-labeled neurons in freely moving C. elegans. We believe that the combined ultrafast speed and large 3D SBP offered by EventLFM may open up new possibilities across many biomedical applications.

Local Conditional Neural Fields for Versatile and Generalizable Large-Scale Reconstructions in Computational Imaging

Deep learning has transformed computational imaging, but traditional pixel-based representations limit their ability to capture continuous, multiscale details of objects. Here we introduce a novel Local Conditional Neural Fields (LCNF) framework, leveraging a continuous implicit neural representation to address this limitation. LCNF enables flexible object representation and facilitates the reconstruction of multiscale information. We demonstrate the capabilities of LCNF in solving the highly ill-posed inverse problem in Fourier ptychographic microscopy (FPM) with multiplexed measurements, achieving robust, scalable, and generalizable large-scale phase retrieval. Unlike traditional neural fields frameworks, LCNF incorporates a local conditional representation that promotes model generalization, learning multiscale information, and efficient processing of large-scale imaging data. By combining an encoder and a decoder conditioned on a learned latent vector, LCNF achieves versatile continuous-domain super-resolution image reconstruction. We demonstrate accurate reconstruction of wide field-of-view, high-resolution phase images using only a few multiplexed measurements. LCNF robustly captures the continuous object priors and eliminates various phase artifacts, even when it is trained on imperfect datasets. The framework exhibits strong generalization, reconstructing diverse objects even with limited training data. Furthermore, LCNF can be trained on a physics simulator using natural images and successfully applied to experimental measurements on biological samples. Our results highlight the potential of LCNF for solving large-scale inverse problems in computational imaging, with broad applicability in various deep-learning-based techniques.

Channel Measurement, Modeling, and Simulation for 6G: A Survey and Tutorial

Technology research and standardization work of sixth generation (6G) has been carried out worldwide. Channel research is the prerequisite of 6G technology evaluation and optimization. This paper presents a survey and tutorial on channel measurement, modeling, and simulation for 6G. We first highlight the challenges of channel for 6G systems, including higher frequency band, extremely large antenna array, new technology combinations, and diverse application scenarios. A review of channel measurement and modeling for four possible 6G enabling technologies is then presented, i.e., terahertz communication, massive multiple-input multiple-output communication, joint communication and sensing, and reconfigurable intelligent surface. Finally, we introduce a 6G channel simulation platform and provide examples of its implementation. The goal of this paper is to help both professionals and non-professionals know the progress of 6G channel research, understand the 6G channel model, and use it for 6G simulation.

3GPP-Like THz Channel Modeling for Indoor Office and Urban Microcellular Scenarios

Terahertz (THz) communication is envisioned as the possible technology for the sixth-generation (6G) communication system. THz channel propagation characteristics are the basis of designing and evaluating for THz communication system. In this paper, THz channel measurements at 100 GHz and 132 GHz are conducted in an indoor office scenario and an urban microcellular (UMi) scenario, respectively. Based on the measurement, the 3GPP-like channel parameters are extracted and analyzed. Moreover, the parameters models are available for the simulation of the channel impulse response by the geometry-based stochastic model (GBSM). Then, the comparisons between measurement-based parameter models and 3rd Generation Partnership Project (3GPP) channel models are investigated. It is observed that the case with path loss approaching free space exists in the NLoS scenario. Besides, the cluster number are 4 at LoS and 5 at NLoS in the indoor office and 4 at LoS and 3 at NLoS in the UMi, which are much less than 3GPP. The multipath component (MPC) in the THz channel distributes more simpler and more sparsely than the 3GPP millimeter wave (mm-wave) channel models. Furthermore, the ergodic capacity of mm-wave and THz are evaluated by the proposed THz GBSM implementation framework. The THz measurement model predicts the smallest capacity, indicating that high carrier frequency is limited to the single transmission mechanism of reflection and results in the reduction of cluster numbers and ergodic capacity. Generally, these results are helpful to understand and model the THz channel and apply the THz communication technique for 6G.

Robust single-shot 3D fluorescence imaging in scattering media with a simulator-trained neural network

Imaging through scattering is a pervasive and difficult problem in many biological applications. The high background and the exponentially attenuated target signals due to scattering fundamentally limits the imaging depth of fluorescence microscopy. Light-field systems are favorable for high-speed volumetric imaging, but the 2D-to-3D reconstruction is fundamentally ill-posed and scattering exacerbates the condition of the inverse problem. Here, we develop a scattering simulator that models low-contrast target signals buried in heterogeneous strong background. We then train a deep neural network solely on synthetic data to descatter and reconstruct a 3D volume from a single-shot light-field measurement with low signal-to-background ratio (SBR). We apply this network to our previously developed Computational Miniature Mesoscope and demonstrate the robustness of our deep learning algorithm on a 75 micron thick fixed mouse brain section and on bulk scattering phantoms with different scattering conditions. The network can robustly reconstruct emitters in 3D with a 2D measurement of SBR as low as 1.05 and as deep as a scattering length. We analyze fundamental tradeoffs based on network design factors and out-of-distribution data that affect the deep learning model's generalizability to real experimental data. Broadly, we believe that our simulator-based deep learning approach can be applied to a wide range of imaging through scattering techniques where experimental paired training data is lacking.