Abstract:We describe our automatic generative algorithm to create street addresses from satellite images by learning and labeling roads, regions, and address cells. Currently, 75% of the world's roads lack adequate street addressing systems. Recent geocoding initiatives tend to convert pure latitude and longitude information into a memorable form for unknown areas. However, settlements are identified by streets, and such addressing schemes are not coherent with the road topology. Instead, we propose a generative address design that maps the globe in accordance with streets. Our algorithm starts with extracting roads from satellite imagery by utilizing deep learning. Then, it uniquely labels the regions, roads, and structures using some graph-and proximity-based algorithms. We also extend our addressing scheme to (i) cover inaccessible areas following similar design principles; (ii) be inclusive and flexible for changes on the ground; and (iii) lead as a pioneer for a unified street-based global geodatabase. We present our results on an example of a developed city and multiple undeveloped cities. We also compare productivity on the basis of current ad hoc and new complete addresses. We conclude by contrasting our generative addresses to current industrial and open solutions.
Depth-based inpainting methods can solve disocclusion problems occurring in depth-image-based rendering. However, inpainting in this context suffers from artifacts along foreground objects due to foreground pixels in the patch matching. In this paper, we address the disocclusion problem by a refined depth-based inpainting method. The novelty is in classifying the foreground and background by using available local depth information. Thereby, the foreground information is excluded from both the source region and the target patch. In the proposed inpainting method, the local depth constraints imply inpainting only the background data and preserving the foreground object boundaries. The results from the proposed method are compared with those from the state-ofthe art inpainting methods. The experimental results demonstrate improved objective quality and a better visual quality along the object boundaries.
Depth-image-based rendering (DIBR) is a commonly used method for synthesizing additional views using video-plus-depth (V+D) format. A critical issue with DIBR-based view synthesis is the lack of information behind foreground objects. This lack is manifested as disocclusions, holes, next to the foreground objects in rendered virtual views as a consequence of the virtual camera "seeing" behind the foreground object. The disocclusions are larger in the extrapolation case, i.e. the single camera case. Texture synthesis methods (inpainting methods) aim to fill these disocclusions by producing plausible texture content. However, virtual views inevitably exhibit both spatial and temporal inconsistencies at the filled disocclusion areas, depending on the scene content. In this paper, we propose a layered depth image (LDI) approach that improves the spatio-temporal consistency. In the process of LDI generation, depth information is used to classify the foreground and background in order to form a static scene sprite from a set of neighboring frames. Occlusions in the LDI are then identified and filled using inpainting, such that no disocclusions appear when the LDI data is rendered to a virtual view. In addition to the depth information, optical flow is computed to extract the stationary parts of the scene and to classify the occlusions in the inpainting process. Experimental results demonstrate that spatio-temporal inconsistencies are significantly reduced using the proposed method. Furthermore, subjective and objective qualities are improved compared to state-of-the-art reference methods.
View synthesis is an efficient solution to produce content for 3DTV and FTV. However, proper handling of the disocclusions is a major challenge in the view synthesis. Inpainting methods offer solutions for handling disocclusions, though limitations in foreground-background classification causes the holes to be filled with inconsistent textures. Moreover, the state-of-the art methods fail to identify and fill disocclusions in intermediate distances between foreground and background through which background may be visible in the virtual view (translucent disocclusions). Aiming at improved rendering quality, we introduce a layered depth image (LDI) in the original camera view, in which we identify and fill occluded background so that when the LDI data is rendered to a virtual view, no disocclusions appear but views with consistent data are produced also handling translucent disocclusions. Moreover, the proposed foreground-background classification and inpainting fills the disocclusions with neighboring background texture consistently. Based on the objective and subjective evaluations, the proposed method outperforms the state-of-the art methods at the disocclusions.
Distribution of future 3DTV is likely to use supplementary depth information to a video sequence. New virtual views may then be rendered in order to adjust to different 3D displays. All depthimaged-based rendering (DIBR) methods suffer from artifacts in the resulting images, which are corrected by different postprocessing. The proposed method is based on fundamental principles of 3D-warping. The novelty lies in how the virtual view sample values are obtained from one-dimensional interpolation, where edges are preserved by introducing specific edge-pixels with information about both foreground and background data. This avoids fully the post-processing of filling cracks and holes. We compared rendered virtual views of our method and of the View Synthesis Reference Software (VSRS) and analyzed the results based on typical artifacts. The proposed method obtained better quality for photographic images and similar quality for synthetic images.Index Terms-3D, video plus depth, warping, depthimage-based view rendering.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.