A5025651569- Advanced Fluorescence Microscopy Techniques
- Optical Coherence Tomography Applications
- Digital Holography and Microscopy
- Cell Image Analysis Techniques
- Photoacoustic and Ultrasonic Imaging
- Image Processing Techniques and Applications
- Optical measurement and interference techniques
- Photonic and Optical Devices
- Neural Networks and Reservoir Computing
- Advanced Vision and Imaging
- Advanced X-ray Imaging Techniques
- Neural dynamics and brain function
- Advanced Optical Sensing Technologies
- Particle physics theoretical and experimental studies
- Optical Network Technologies
- Quantum Chromodynamics and Particle Interactions
- Random lasers and scattering media
- Advanced Memory and Neural Computing
- Advanced Electron Microscopy Techniques and Applications
- Adaptive optics and wavefront sensing
- Metamaterials and Metasurfaces Applications
- Advanced Image Processing Techniques
- High-Energy Particle Collisions Research
- Reproductive biology and impacts on aquatic species
- Image and Signal Denoising Methods
Tsinghua University
2016-2025
University of Hong Kong
2020-2025
Beijing Municipal Education Commission
2022-2024
Chinese Institute for Brain Research
2021-2024
McGovern Institute for Brain Research
2024
China West Normal University
2024
Minjiang University
2024
University of British Columbia
2024
Shanghai Artificial Intelligence Laboratory
2024
Beijing Academy of Artificial Intelligence
2024
In this Letter we propose the Fourier-space diffractive deep neural network (F-D^{2}NN) for all-optical image processing that performs advanced computer vision tasks at speed of light. The F-D^{2}NN is achieved by placing extremely compact modulation layers Fourier plane or both and imaging planes an optical system, where nonlinearity introduced from ferroelectric thin films. We demonstrated can be trained with learning algorithms saliency detection high-accuracy object classification.
This paper proposes a novel compressive hyperspectral (HS) imaging approach that allows for high-resolution HS images to be captured in single image. The proposed architecture comprises three key components: spatial-spectral encoded optical camera design, over-complete dictionary learning and sparse-constraint computational reconstruction. Our sampling scheme provides higher degree of randomness the measured projections than previous approaches; robust nonlinear sparse reconstruction method...
Underwater image enhancement aims at improving the visibility and eliminating color distortions of underwater images degraded by light absorption scattering in water. Recently, retinex variational models show remarkable capacity enhancing estimating reflectance illumination a decomposition course. However, ambiguous details unnatural still challenge performance on enhancement. To overcome these limitations, we propose hyper-laplacian priors inspired model to enhance images. Specifically, are...
Training an artificial neural network with backpropagation algorithms to perform advanced machine learning tasks requires extensive computational process. This paper proposes implement the algorithm optically for in situ training of both linear and nonlinear diffractive optical networks, which enables acceleration speed improvement energy efficiency on core computing modules. We demonstrate that gradient a loss function respect weights layers can be accurately calculated by measuring forward...
Abstract A fundamental challenge in fluorescence microscopy is the photon shot noise arising from inevitable stochasticity of detection. Noise increases measurement uncertainty and limits imaging resolution, speed sensitivity. To achieve high-sensitivity beyond shot-noise limit, we present DeepCAD-RT, a self-supervised deep learning method for real-time suppression. Based on our previous framework DeepCAD, reduced number network parameters by 94%, memory consumption 27-fold processing time...
Abstract Photonic computing enables faster and more energy-efficient processing of vision data 1–5 . However, experimental superiority deployable systems remains a challenge because complicated optical nonlinearities, considerable power consumption analog-to-digital converters (ADCs) for downstream digital vulnerability to noises system errors 1,6–8 Here we propose an all-analog chip combining electronic light (ACCEL). It has systemic energy efficiency 74.8 peta-operations per second watt...
Abstract Planar digital image sensors facilitate broad applications in a wide range of areas 1–5 , and the number pixels has scaled up rapidly recent years 2,6 . However, practical performance imaging systems is fundamentally limited by spatially nonuniform optical aberrations originating from imperfect lenses or environmental disturbances 7,8 Here we propose an integrated scanning light-field sensor, termed meta-imaging to achieve high-speed aberration-corrected three-dimensional...
Holistic understanding of physio-pathological processes requires noninvasive 3D imaging in deep tissue across multiple spatial and temporal scales to link diverse transient subcellular behaviors with long-term physiogenesis. Despite broad applications two-photon microscopy (TPM), there remains an inevitable tradeoff among spatiotemporal resolution, volumes, durations due the point-scanning scheme, accumulated phototoxicity, optical aberrations. Here, we harnessed concept synthetic aperture...
Abstract Computational super-resolution methods, including conventional analytical algorithms and deep learning models, have substantially improved optical microscopy. Among them, supervised neural networks demonstrated outstanding performance, however, demanding abundant high-quality training data, which are laborious even impractical to acquire due the high dynamics of living cells. Here, we develop zero-shot deconvolution (ZS-DeconvNet) that instantly enhance resolution microscope images...
Abstract Long-term observation of subcellular dynamics in living organisms is limited by background fluorescence originating from tissue scattering or dense labeling. Existing confocal approaches face an inevitable tradeoff among parallelization, resolution and phototoxicity. Here we present scanning light-field microscopy (csLFM), which integrates axially elongated line-confocal illumination with the rolling shutter (sLFM). csLFM enables high-fidelity, high-speed, three-dimensional (3D)...
This paper proposes a novel approach for high-resolution light field microscopy imaging by using camera array. In this approach, we apply two-stage relay system expanding the aperture plane of microscope into size an lens array, and utilize sensor array acquiring different sub-apertures images formed corresponding lenses. By combining rectified synchronized from 5 × viewpoints with our prototype system, successfully recovered color videos various fast-moving microscopic specimens spatial...
Abstract The development of deep learning and open access to a substantial collection imaging data together provide potential solution for computational image transformation, which is gradually changing the landscape optical biomedical research. However, current implementations usually operate in supervised manner, their reliance on laborious error-prone annotation procedures remains barrier more general applicability. Here, we propose an unsupervised transformation facilitate utilization...
Reviewing the history of development artificial intelligence (AI) clearly reveals that brain science has resulted in breakthroughs AI, such as deep learning. At present, although developmental trend AI and its applications surpassed expectations, an insurmountable gap remains between human intelligence. It is urgent to establish a bridge research, including link from connection knowing simulating brain. The first steps toward this goal are explore secrets by studying new brain-imaging...
The rapid development of artificial intelligence (AI) facilitates various applications from all areas but also poses great challenges in its hardware implementation terms speed and energy because the explosive growth data. Optical computing provides a distinctive perspective to address this bottleneck by harnessing unique properties photons including broad bandwidth, low latency, high efficiency. In review, we introduce latest developments optical for different AI models, feedforward neural...
Following the explosive growth of global data, there is an ever-increasing demand for high-throughput processing in image transmission systems. However, existing methods mainly rely on electronic circuits, which severely limits throughput. Here, we propose end-to-end all-optical variational autoencoder, named photonic encoder-decoder (PED), maps physical system into optical generative neural network. By modeling noises as variation latent space, PED establishes a large-scale unsupervised...
Abstract Widefield microscopy can provide optical access to multi-millimeter fields of view and thousands neurons in mammalian brains at video rate. However, tissue scattering background contamination results signal deterioration, making the extraction neuronal activity challenging, laborious time consuming. Here we present our deep-learning-based widefield neuron finder (DeepWonder), which is trained by simulated functional recordings effectively works on experimental data achieve...
Abstract High-speed three-dimensional (3D) intravital imaging in animals is useful for studying transient subcellular interactions and functions health disease. Light-field microscopy (LFM) provides a computational solution snapshot 3D with low phototoxicity but restricted by resolution reconstruction artifacts induced optical aberrations, motion noise. Here, we propose virtual-scanning LFM (VsLFM), physics-based deep learning framework to increase the of up diffraction limit within...