@article{StojanovicTrappRichteretal.2019, author = {Stojanovic, Vladeta and Trapp, Matthias and Richter, Rico and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {Service-oriented semantic enrichment of indoor point clouds using octree-based multiview classification}, series = {Graphical Models}, volume = {105}, journal = {Graphical Models}, publisher = {Elsevier}, address = {San Diego}, issn = {1524-0703}, doi = {10.1016/j.gmod.2019.101039}, pages = {18}, year = {2019}, abstract = {The use of Building Information Modeling (BIM) for Facility Management (FM) in the Operation and Maintenance (O\&M) stages of the building life-cycle is intended to bridge the gap between operations and digital data, but lacks the functionality of assessing the state of the built environment due to non-automated generation of associated semantics. 3D point clouds can be used to capture the physical state of the built environment, but also lack these associated semantics. A prototypical implementation of a service-oriented architecture for classification of indoor point cloud scenes of office environments is presented, using multiview classification. The multiview classification approach is tested using a retrained Convolutional Neural Network (CNN) model - Inception V3. The presented approach for classifying common office furniture objects (chairs, sofas and desks), contained in 3D point cloud scans, is tested and evaluated. The results show that the presented approach can classify common office furniture up to an acceptable degree of accuracy, and is suitable for quick and robust semantics approximation - based on RGB (red, green and blue color channel) cubemap images of the octree partitioned areas of the 3D point cloud scan. Additional methods for web-based 3D visualization, editing and annotation of point clouds are also discussed. Using the described approach, captured scans of indoor environments can be semantically enriched using object annotations derived from multiview classification results. Furthermore, the presented approach is suited for semantic enrichment of lower resolution indoor point clouds acquired using commodity mobile devices.}, language = {en} } @misc{FlorioTrappDoellner2019, author = {Florio, Alessandro and Trapp, Matthias and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {Semantic-driven Visualization Techniques for Interactive Exploration of 3D Indoor Models}, series = {2019 23rd International Conference Information Visualisation (IV)}, journal = {2019 23rd International Conference Information Visualisation (IV)}, publisher = {Inst. of Electr. and Electronics Engineers}, address = {Los Alamitos}, isbn = {978-1-7281-2838-2}, issn = {2375-0138}, doi = {10.1109/IV.2019.00014}, pages = {25 -- 30}, year = {2019}, abstract = {The availability of detailed virtual 3D building models including representations of indoor elements, allows for a wide number of applications requiring effective exploration and navigation functionality. Depending on the application context, users should be enabled to focus on specific Objects-of-Interests (OOIs) or important building elements. This requires approaches to filtering building parts as well as techniques to visualize important building objects and their relations. For it, this paper explores the application and combination of interactive rendering techniques as well as their semanticallydriven configuration in the context of 3D indoor models.}, language = {en} } @misc{TrappDoellner2019, author = {Trapp, Matthias and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {Real-time Screen-space Geometry Draping for 3D Digital Terrain Models}, series = {2019 23rd International Conference Information Visualisation (IV)}, journal = {2019 23rd International Conference Information Visualisation (IV)}, publisher = {Inst. of Electr. and Electronics Engineers}, address = {Los Alamitos}, isbn = {978-1-7281-2838-2}, issn = {2375-0138}, doi = {10.1109/IV.2019.00054}, pages = {281 -- 286}, year = {2019}, abstract = {A fundamental task in 3D geovisualization and GIS applications is the visualization of vector data that can represent features such as transportation networks or land use coverage. Mapping or draping vector data represented by geometric primitives (e.g., polylines or polygons) to 3D digital elevation or 3D digital terrain models is a challenging task. We present an interactive GPU-based approach that performs geometry-based draping of vector data on per-frame basis using an image-based representation of a 3D digital elevation or terrain model only.}, language = {en} } @article{PasewaldtSemmoTrappetal.2014, author = {Pasewaldt, Sebastian and Semmo, Amir and Trapp, Matthias and D{\"o}llner, J{\"u}rgen}, title = {Multi-perspective 3D panoramas}, series = {International journal of geographical information science}, volume = {28}, journal = {International journal of geographical information science}, number = {10}, publisher = {Routledge, Taylor \& Francis Group}, address = {Abingdon}, issn = {1365-8816}, doi = {10.1080/13658816.2014.922686}, pages = {2030 -- 2051}, year = {2014}, abstract = {This article presents multi-perspective 3D panoramas that focus on visualizing 3D geovirtual environments (3D GeoVEs) for navigation and exploration tasks. Their key element, a multi-perspective view (MPV), seamlessly combines what is seen from multiple viewpoints into a single image. This approach facilitates the presentation of information for virtual 3D city and landscape models, particularly by reducing occlusions, increasing screen-space utilization, and providing additional context within a single image. We complement MPVs with cartographic visualization techniques to stylize features according to their semantics and highlight important or prioritized information. When combined, both techniques constitute the core implementation of interactive, multi-perspective 3D panoramas. They offer a large number of effective means for visual communication of 3D spatial information, a high degree of customization with respect to cartographic design, and manifold applications in different domains. We discuss design decisions of 3D panoramas for the exploration of and navigation in 3D GeoVEs. We also discuss a preliminary user study that indicates that 3D panoramas are a promising approach for navigation systems using 3D GeoVEs.}, language = {en} } @misc{LimbergerScheibelTrappetal.2017, author = {Limberger, Daniel and Scheibel, Willy and Trapp, Matthias and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {Mixed-projection treemaps}, series = {21st International Conference Information Visualisation (IV)}, journal = {21st International Conference Information Visualisation (IV)}, publisher = {Institute of Electrical and Electronics Engineers}, address = {Los Alamitos}, isbn = {978-1-5386-0831-9}, issn = {2375-0138}, doi = {10.1109/iV.2017.67}, pages = {164 -- 169}, year = {2017}, abstract = {This paper presents a novel technique for combining 2D and 2.5D treemaps using multi-perspective views to leverage the advantages of both treemap types. It enables a new form of overview+detail visualization for tree-structured data and contributes new concepts for real-time rendering of and interaction with treemaps. The technique operates by tilting the graphical elements representing inner nodes using affine transformations and animated state transitions. We explain how to mix orthogonal and perspective projections within a single treemap. Finally, we show application examples that benefit from the reduced interaction overhead.}, language = {en} } @misc{ReimannKlingbeilPasewaldtetal.2018, author = {Reimann, Max and Klingbeil, Mandy and Pasewaldt, Sebastian and Semmo, Amir and Trapp, Matthias and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {MaeSTrO: A Mobile App for Style Transfer Orchestration using Neural Networks}, series = {International Conference on Cyberworlds (CW)}, journal = {International Conference on Cyberworlds (CW)}, editor = {Sourin, A Sourina}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-7315-7}, doi = {10.1109/CW.2018.00016}, pages = {9 -- 16}, year = {2018}, abstract = {Mobile expressive rendering gained increasing popularity among users seeking casual creativity by image stylization and supports the development of mobile artists as a new user group. In particular, neural style transfer has advanced as a core technology to emulate characteristics of manifold artistic styles. However, when it comes to creative expression, the technology still faces inherent limitations in providing low-level controls for localized image stylization. This work enhances state-of-the-art neural style transfer techniques by a generalized user interface with interactive tools to facilitate a creative and localized editing process. Thereby, we first propose a problem characterization representing trade-offs between visual quality, run-time performance, and user control. We then present MaeSTrO, a mobile app for orchestration of neural style transfer techniques using iterative, multi-style generative and adaptive neural networks that can be locally controlled by on-screen painting metaphors. At this, first user tests indicate different levels of satisfaction for the implemented techniques and interaction design.}, language = {en} } @article{ReimannKlingbeilPasewaldtetal.2019, author = {Reimann, Max and Klingbeil, Mandy and Pasewaldt, Sebastian and Semmo, Amir and Trapp, Matthias and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {Locally controllable neural style transfer on mobile devices}, series = {The Visual Computer}, volume = {35}, journal = {The Visual Computer}, number = {11}, publisher = {Springer}, address = {New York}, issn = {0178-2789}, doi = {10.1007/s00371-019-01654-1}, pages = {1531 -- 1547}, year = {2019}, abstract = {Mobile expressive rendering gained increasing popularity among users seeking casual creativity by image stylization and supports the development of mobile artists as a new user group. In particular, neural style transfer has advanced as a core technology to emulate characteristics of manifold artistic styles. However, when it comes to creative expression, the technology still faces inherent limitations in providing low-level controls for localized image stylization. In this work, we first propose a problem characterization of interactive style transfer representing a trade-off between visual quality, run-time performance, and user control. We then present MaeSTrO, a mobile app for orchestration of neural style transfer techniques using iterative, multi-style generative and adaptive neural networks that can be locally controlled by on-screen painting metaphors. At this, we enhance state-of-the-art neural style transfer techniques by mask-based loss terms that can be interactively parameterized by a generalized user interface to facilitate a creative and localized editing process. We report on a usability study and an online survey that demonstrate the ability of our app to transfer styles at improved semantic plausibility.}, language = {en} } @article{SemmoTrappKyprianidisetal.2012, author = {Semmo, Amir and Trapp, Matthias and Kyprianidis, Jan Eric and D{\"o}llner, J{\"u}rgen Roland Friedrich}, title = {Interactive visualization of generalized virtual 3D city models using level-of-abstraction transitions}, series = {Computer graphics forum : journal of the European Association for Computer Graphics}, volume = {31}, journal = {Computer graphics forum : journal of the European Association for Computer Graphics}, number = {3}, publisher = {Wiley-Blackwell}, address = {Hoboken}, issn = {0167-7055}, doi = {10.1111/j.1467-8659.2012.03081.x}, pages = {885 -- 894}, year = {2012}, abstract = {Virtual 3D city models play an important role in the communication of complex geospatial information in a growing number of applications, such as urban planning, navigation, tourist information, and disaster management. In general, homogeneous graphic styles are used for visualization. For instance, photorealism is suitable for detailed presentations, and non-photorealism or abstract stylization is used to facilitate guidance of a viewer's gaze to prioritized information. However, to adapt visualization to different contexts and contents and to support saliency-guided visualization based on user interaction or dynamically changing thematic information, a combination of different graphic styles is necessary. Design and implementation of such combined graphic styles pose a number of challenges, specifically from the perspective of real-time 3D visualization. In this paper, the authors present a concept and an implementation of a system that enables different presentation styles, their seamless integration within a single view, and parametrized transitions between them, which are defined according to tasks, camera view, and image resolution. The paper outlines potential usage scenarios and application fields together with a performance evaluation of the implementation.}, language = {en} } @phdthesis{Trapp2013, author = {Trapp, Matthias}, title = {Interactive rendering techniques for focus+context visualization of 3D geovirtual environments}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-66824}, school = {Universit{\"a}t Potsdam}, year = {2013}, abstract = {This thesis introduces a collection of new real-time rendering techniques and applications for focus+context visualization of interactive 3D geovirtual environments such as virtual 3D city and landscape models. These environments are generally characterized by a large number of objects and are of high complexity with respect to geometry and textures. For these reasons, their interactive 3D rendering represents a major challenge. Their 3D depiction implies a number of weaknesses such as occlusions, cluttered image contents, and partial screen-space usage. To overcome these limitations and, thus, to facilitate the effective communication of geo-information, principles of focus+context visualization can be used for the design of real-time 3D rendering techniques for 3D geovirtual environments (see Figure). In general, detailed views of a 3D geovirtual environment are combined seamlessly with abstracted views of the context within a single image. To perform the real-time image synthesis required for interactive visualization, dedicated parallel processors (GPUs) for rasterization of computer graphics primitives are used. For this purpose, the design and implementation of appropriate data structures and rendering pipelines are necessary. The contribution of this work comprises the following five real-time rendering methods: • The rendering technique for 3D generalization lenses enables the combination of different 3D city geometries (e.g., generalized versions of a 3D city model) in a single image in real time. The method is based on a generalized and fragment-precise clipping approach, which uses a compressible, raster-based data structure. It enables the combination of detailed views in the focus area with the representation of abstracted variants in the context area. • The rendering technique for the interactive visualization of dynamic raster data in 3D geovirtual environments facilitates the rendering of 2D surface lenses. It enables a flexible combination of different raster layers (e.g., aerial images or videos) using projective texturing for decoupling image and geometry data. Thus, various overlapping and nested 2D surface lenses of different contents can be visualized interactively. • The interactive rendering technique for image-based deformation of 3D geovirtual environments enables the real-time image synthesis of non-planar projections, such as cylindrical and spherical projections, as well as multi-focal 3D fisheye-lenses and the combination of planar and non-planar projections. • The rendering technique for view-dependent multi-perspective views of 3D geovirtual environments, based on the application of global deformations to the 3D scene geometry, can be used for synthesizing interactive panorama maps to combine detailed views close to the camera (focus) with abstract views in the background (context). This approach reduces occlusions, increases the usage the available screen space, and reduces the overload of image contents. • The object-based and image-based rendering techniques for highlighting objects and focus areas inside and outside the view frustum facilitate preattentive perception. The concepts and implementations of interactive image synthesis for focus+context visualization and their selected applications enable a more effective communication of spatial information, and provide building blocks for design and development of new applications and systems in the field of 3D geovirtual environments.}, language = {en} } @article{ShekharReimannMayeretal.2021, author = {Shekhar, Sumit and Reimann, Max and Mayer, Maximilian and Semmo, Amir and Pasewaldt, Sebastian and D{\"o}llner, J{\"u}rgen and Trapp, Matthias}, title = {Interactive photo editing on smartphones via intrinsic decomposition}, series = {Computer graphics forum : journal of the European Association for Computer Graphics}, volume = {40}, journal = {Computer graphics forum : journal of the European Association for Computer Graphics}, publisher = {Blackwell}, address = {Oxford}, issn = {0167-7055}, doi = {10.1111/cgf.142650}, pages = {497 -- 510}, year = {2021}, abstract = {Intrinsic decomposition refers to the problem of estimating scene characteristics, such as albedo and shading, when one view or multiple views of a scene are provided. The inverse problem setting, where multiple unknowns are solved given a single known pixel-value, is highly under-constrained. When provided with correlating image and depth data, intrinsic scene decomposition can be facilitated using depth-based priors, which nowadays is easy to acquire with high-end smartphones by utilizing their depth sensors. In this work, we present a system for intrinsic decomposition of RGB-D images on smartphones and the algorithmic as well as design choices therein. Unlike state-of-the-art methods that assume only diffuse reflectance, we consider both diffuse and specular pixels. For this purpose, we present a novel specularity extraction algorithm based on a multi-scale intensity decomposition and chroma inpainting. At this, the diffuse component is further decomposed into albedo and shading components. We use an inertial proximal algorithm for non-convex optimization (iPiano) to ensure albedo sparsity. Our GPU-based visual processing is implemented on iOS via the Metal API and enables interactive performance on an iPhone 11 Pro. Further, a qualitative evaluation shows that we are able to obtain high-quality outputs. Furthermore, our proposed approach for specularity removal outperforms state-of-the-art approaches for real-world images, while our albedo and shading layer decomposition is faster than the prior work at a comparable output quality. Manifold applications such as recoloring, retexturing, relighting, appearance editing, and stylization are shown, each using the intrinsic layers obtained with our method and/or the corresponding depth data.}, language = {en} }