133-MEGAPIXEL1 MICRON PIXELS1st and 2nd FM generation 3D halftoning108 Megapixel1/f noise100 Hue test1-bit matrix completion180 degree images
2
2D and 3D video2D-plus-depth video2D to Hologram conversion2D metrics2-d scale2.5D reconstruction2D DCT2D VIEWS2-D barcodes2D-TO-3D CONVERSION ARTIFACTS2D printing2D2.5D2AFC2.5D printing2D AND 3D CONVERTIBLE DISPLAY2.5 D printing2D/3D imaging, high performance computing, imaging systems, efficient computations and storage2.5D PRINTING
3
360VR3D/4D Data Processing and Filtering3D mapping and localization360-video3D depth-map360-degree video streaming3D optical scans3D data processing3D surface3D Saliency3D objects3D warping3D scene classification3D video processing3D refinement3D display3D-color perception3D mesh3D shape indexing and retrieval3D Telepresence3D Data Processing3D-shooting3D position measurement of people3D DIGITIZATION METHOD FOR OIL PAINTINGS3D theater program listing3D Measurement3D MODEL3D PRINTING3D face alignment360-degree images3D Object Detection3D Morphable Model3D perception360 panorama3D stereo vision360-degree image projection360 degrees video360-degree art exhibition3D CAMERAS3D-LUT3D video3D/4D Scanning3D PRINTER3D shape360-degree content3D Communications3D printing3D affine transformation3D Point Cloud3D Printing3D recovery3D modelling3D capture3D Mapping3D scanning3D Range Data Compression360 degree images3D Immersion3D Vision3D digital halftoning3D RECONSTRUCTION3D rigid transformations3D modeling3D/2D Visuals3D depth sensing360° video3ARRI footage3D Curvelet3D range scanning3D HALFTONING360 IMAGING360-degree Image3D Imaging3D compression3D model3D TRANSFORMATION3D Modeling3D STACK3D surface reproduction3D Range Data3D Tracking3D EDUCATIONAL MATERIAL3D/4D DATA PROCESSING AND FILTERING3D Shape Indexing and Retrieval3D Video Communications3D scene flow estimation3D connected tube model360-degree videos3D adaptive halftoning3D-HEVC3D camera3D Data Sources3D Halftoning3D Digital Image Correlation3D image compression3D DISPLAY3D visual representation3D-high efficiency video coding3A ALGORITHMS360 Video3d mapping3-D SHAPE RECOVERY360x3D scene capture3D cinema and TV360-Degree Video Technology3D PROFILE3D TV3D USER INTERFACES3d3D Range Data Encoding3D-printing3D Color Printing360-degree imaging3D Reconstruction3D surface structure based halftoning3D COMPRESSION AND ENCRYPTION3D glasses3D3D encoding3D vision3D IMAGE3D STIMULI3d video35MM FILM DIGITIZATION3D mesh simplification3D projector3D point cloud3D human-centered technologies3D-Anisotropic smoothing3DCNN3D Scene Reconstruction and Modeling3D-assisted features3D localization3D/4D SCANNING3D range geometry3D localization and mapping3D digitization and dissemination3D Print Appearance3D colour Digital Image Correlation3D printer3D RECOVERY3D imaging3D audio3D ACQUISITION ARCHITECTURE3D INTERACTION360° VIDEO3D halftoning3D print3D Video3-T pixel3D-human body detection3D recursive search3D Meshes3D SALIENCY3D SHAPE INDEXING AND RETRIEVAL3D SCENE RECONSTRUCTION AND MODELING3D and 2D3-D RECONSTRUCTION3D MODELLING3d localization3D Image Processing3D RANGE IMAGING3D Video Conferencing3D Quality360-deg quality assessment360-DEGREE IMAGE3D shape analysis3D Compression3D Computer Graphics3D object shape3D Models3D Gaussian splatting3D Display3D MESHES360-degree3D displays3D communications360-degree video3DSR3D-CNN3D Scene Reconstruction3D Lidar3D MESH3D Iterative Halftoning360° STEREO PANORAMAS3D reconstruction3DMM3D Compression and Encryption3D VISUALIZATION
Our central goal was to create automatic methods for semantic segmentation of human figures in images of fine art paintings. This is a difficult problem because the visual properties and statistics of artwork differ markedly from the natural photographs widely used in research in automatic segmentation. We used a deep neural network to transfer artistic style from paintings across several centuries to modern natural photographs in order to create a large data set of surrogate art images. We then used this data set to train a separate deep network for semantic image segmentation of genuine art images. Such data augmentation led to great improvement in the segmentation of difficult genuine artworks, revealed both qualitatively and quantitatively. Our unique technique of creating surrogate artworks should find wide use in many tasks in the growing field of computational analysis of fine art.