yoloYouTubeYou only look once v3 (YOLOv3)YOLOv5YOLOv8YOLO-RYOLOYolov5You only look once (YOLO)YOLOv7-tinyYOLOX
Z
Z numberZEISSZERNIKEZoom FatigueZero Parallax SettingZ-type SchlierenZero-Shot ClassificationZERNIKE MOMENTSZernike polynomialZebra Embryo
0
0.8um pixel
1
1-bit matrix completion180 degree images100 Hue test1/f noise108 Megapixel1st and 2nd FM generation 3D halftoning133-MEGAPIXEL1 MICRON PIXELS
2
2.5D printing2D AND 3D CONVERTIBLE DISPLAY2.5 D printing2D/3D imaging, high performance computing, imaging systems, efficient computations and storage2.5D PRINTING2-D barcodes2D-TO-3D CONVERSION ARTIFACTS2D printing2.5D2D2AFC2.5D reconstruction2D DCT2D VIEWS2D and 3D video2D-plus-depth video2D to Hologram conversion2-d scale2D metrics
3
3D SCENE RECONSTRUCTION AND MODELING3D and 2D3D SHAPE INDEXING AND RETRIEVAL3D Meshes3D SALIENCY3D halftoning3D print3D Video3-T pixel3D-human body detection3D recursive search3D Compression3D Computer Graphics3D object shape3D Models3D Video Conferencing3D Quality360-deg quality assessment360-DEGREE IMAGE3D shape analysis3-D RECONSTRUCTION3D MODELLING3d localization3D Image Processing3D RANGE IMAGING3DSR3D displays3DViewers3D communications360-degree video3D Display3D MESHES360-degree3D Gaussian splatting3DMM3D Compression and Encryption3D VISUALIZATION3D reconstruction3D MESH3D Iterative Halftoning360° STEREO PANORAMAS3D-CNN3D Scene Reconstruction3D Lidar3D USER INTERFACES3D cinema and TV360-Degree Video Technology3D PROFILE3D TV3A ALGORITHMS360 Video3d mapping3-D SHAPE RECOVERY360x3D scene capture3D DISPLAY3D visual representation3D-high efficiency video coding3D IMAGE3D STIMULI3d video3D surface structure based halftoning3D COMPRESSION AND ENCRYPTION3D glasses3D3D encoding3D vision3D Color Printing360-degree imaging3D Reconstruction3d3D Range Data Encoding3D-printing3D localization3D/4D SCANNING3D-assisted features3D human-centered technologies3D point cloud3D-Anisotropic smoothing3DCNN3D Scene Reconstruction and Modeling35MM FILM DIGITIZATION3D mesh simplification3D projector3D printer3D RECOVERY3D imaging3D audio3D ACQUISITION ARCHITECTURE3D INTERACTION360° VIDEO3D localization and mapping3D digitization and dissemination3D Print Appearance3D colour Digital Image Correlation3D range geometry3D modelling3D capture3D Mapping3D scanning3D Range Data Compression360 degree images3D affine transformation3D Point Cloud3D Printing3D recovery360-degree content3D Communications3D printing3D PRINTER3D shape3D HALFTONING360 IMAGING3D depth sensing360° video3ARRI footage3D Curvelet3D range scanning3D modeling3D/2D Visuals3D Immersion3D Vision3D digital halftoning3D RECONSTRUCTION3D rigid transformations3D surface reproduction3D Range Data3D Modeling3D STACK3D Imaging3D compression3D model3D TRANSFORMATION360-degree Image3D Digital Image Correlation3D image compression3D adaptive halftoning3D-HEVC3D camera3D Data Sources3D Halftoning3D/4D DATA PROCESSING AND FILTERING3D Shape Indexing and Retrieval3D Video Communications3D scene flow estimation3D connected tube model360-degree videos3D Tracking3D EDUCATIONAL MATERIAL360-video3D depth-map360-degree video streaming3D mapping and localization360VR3D/4D Data Processing and Filtering3D scene classification3D video processing3D objects3D warping3D surface3D Saliency3D optical scans3D data processing3D theater program listing3D Measurement3D Telepresence3D Data Processing3D-shooting3D position measurement of people3D DIGITIZATION METHOD FOR OIL PAINTINGS3D mesh3D shape indexing and retrieval3D refinement3D display3D-color perception3D-LUT3D video3D/4D Scanning3D perception360 panorama3D stereo vision360-degree image projection360 degrees video360-degree art exhibition3D CAMERAS360-degree images3D Object Detection3D Morphable Model3D MODEL3D PRINTING3D face alignment
We propose a neural network architecture combined with specific training and inference procedures for linear inverse problems arising in computational imaging to reconstruct the underlying image and to represent the uncertainty about the reconstruction. The proposed architecture
is built from the model-based reconstruction perspective, which enforces data consistency and eliminates the artifacts in an alternating manner. The training and the inference procedures are based on performing approximate Bayesian analysis on the weights of the proposed network using a variational
inference method. The proposed architecture with the associated inference procedure is capable of characterizing uncertainty while performing reconstruction with a modelbased approach. We tested the proposed method on a simulated magnetic resonance imaging experiment. We showed that the proposed
method achieved an adequate reconstruction capability and provided reliable uncertainty estimates in the sense that the regions having high uncertainty provided by the proposed method are likely to be the regions where reconstruction errors occur.