1 MICRON PIXELS133-MEGAPIXEL1st and 2nd FM generation 3D halftoning100 Hue test108 Megapixel1/f noise1-bit matrix completion180 degree images
2
2D metrics2-d scale2D to Hologram conversion2D-plus-depth video2D and 3D video2D DCT2D VIEWS2.5D reconstruction2AFC2D2.5D2D printing2-D barcodes2D-TO-3D CONVERSION ARTIFACTS2x2 On-chip Lens2D/3D imaging, high performance computing, imaging systems, efficient computations and storage2.5D PRINTING2.5 D printing2D AND 3D CONVERTIBLE DISPLAY2.5D printing
3
360 panorama3D perception3D stereo vision360-degree image projection3D CAMERAS360 degrees video360-degree art exhibition3D-LUT3D video3D/4D Scanning3D face alignment3D PRINTING3D MODEL3D Object Detection360-degree images3D Morphable Model3D Data Processing3D Telepresence3D position measurement of people3D-shooting3D DIGITIZATION METHOD FOR OIL PAINTINGS3DLUT3D Measurement3D theater program listing3D refinement3D display3D-color perception3D mesh3D shape indexing and retrieval3D objects3D warping3D scene classification3D video processing3D data processing3D optical scans3D Saliency3D surface3D Gaussian Splatting360-video3D depth-map360-degree video streaming360VR3D/4D Data Processing and Filtering3D mapping and localization3D adaptive halftoning3D-HEVC3D camera3D Halftoning3D Data Sources3D Digital Image Correlation3D image compression3D Tracking3D EDUCATIONAL MATERIAL3D/4D DATA PROCESSING AND FILTERING3D Shape Indexing and Retrieval3D Video Communications360-degree videos3D connected tube model3D scene flow estimation3D Modeling3D STACK3D surface reproduction3D Range Data360-degree Image3D compression3D Imaging3D model3D TRANSFORMATION3D depth sensing3ARRI footage3D Curvelet360° video3D range scanning3D HALFTONING360 IMAGING3D digital halftoning3D Immersion3D Vision3D rigid transformations3D RECONSTRUCTION3D modeling3D/2D Visuals3D affine transformation3D Point Cloud3D Printing3D recovery3D modelling3D Mapping3D scanning3D capture3D Range Data Compression360 degree images3D PRINTER3D shape360-degree content3D Communications3D printing3D printer3D RECOVERY3D ACQUISITION ARCHITECTURE3D imaging3D audio360° VIDEO3D INTERACTION3D range geometry3D localization and mapping3D digitization and dissemination3D colour Digital Image Correlation3D Print Appearance3D-assisted features3D localization3D/4D SCANNING35MM FILM DIGITIZATION3D mesh simplification3D projector3D point cloud3D human-centered technologies3DCNN3D-Anisotropic smoothing3D Scene Reconstruction and Modeling3D COMPRESSION AND ENCRYPTION3D glasses3D surface structure based halftoning3D encoding3D3D vision3D IMAGE3D STIMULI3d video3D Range Data Encoding3d3D-printing3D Color Printing360-degree imaging3D CG Image3D Reconstruction3D cinema and TV3D PROFILE360-Degree Video Technology3D TV3D USER INTERFACES3D DISPLAY3D visual representation3D-high efficiency video coding3A ALGORITHMS360 Video3d mapping3-D SHAPE RECOVERY360x3D scene capture3D reconstruction3D VISUALIZATION3D Compression and Encryption3DMM3D-CNN3D Scene Reconstruction3D Lidar3D MESH360° STEREO PANORAMAS3D Iterative Halftoning3D displays3DViewers360-degree video3D communications3DSR3D Gaussian splatting3D Display3D MESHES360-degree3D object shape3D Computer Graphics3D Compression3D Models3D MODELLING3-D RECONSTRUCTION3d localization3D RANGE IMAGING3D Image Processing3D Quality3D Video Conferencing360-DEGREE IMAGE360-deg quality assessment3D shape analysis3D SHAPE INDEXING AND RETRIEVAL3D SCENE RECONSTRUCTION AND MODELING3D and 2D3D halftoning3D print3-T pixel3D Video3D recursive search3D-human body detection3D Meshes3D SALIENCY
Training deep models that can be deployed on embedded systems to robustly detect and track highly specialized industrial objects in a variety of field environments remains very challenging. Large Deep Foundation models (e.g., [yuan21]) make it easier than ever to detect and track everyday objects but do not work as well for specialized industrial objects. These models are often very large and not suitable for deployment on embedded systems. In this work we show that the use of a chroma-key like substitution combined with artificial occlusion generation allows one to capture a small number of images of objects under a fixed background in the lab and then generalize them to novel backgrounds that work in the real world under realistic conditions improving detection of occluded objects by 4% and improving detection in different environments by 44% over state-of-the-art augmentation methods such as MOSAIC.