15 results
Search Results
Now showing 1 - 10 of 15
Item Austrian Chapter Report(2024-04-22) Wimmer, MichaelItem PPSurf: Combining Patches and Point Convolutions for Detailed Surface Reconstruction(© 2024 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2024) Erler, Philipp; Fuentes‐Perez, Lizeth; Hermosilla, Pedro; Guerrero, Paul; Pajarola, Renato; Wimmer, Michael; Alliez, Pierre; Wimmer, Michael3D surface reconstruction from point clouds is a key step in areas such as content creation, archaeology, digital cultural heritage and engineering. Current approaches either try to optimize a non‐data‐driven surface representation to fit the points, or learn a data‐driven prior over the distribution of commonly occurring surfaces and how they correlate with potentially noisy point clouds. Data‐driven methods enable robust handling of noise and typically either focus on a or a prior, which trade‐off between robustness to noise on the global end and surface detail preservation on the local end. We propose as a method that combines a global prior based on point convolutions and a local prior based on processing local point cloud patches. We show that this approach is robust to noise while recovering surface details more accurately than the current state‐of‐the‐art. Our source code, pre‐trained model and dataset are available at .Item Eurographics - CESCG support application(2024-04-17) Wimmer, MichaelThis proposal is to support the Central European Seminar for Computer Graphics (CESCG) with a yearly flat sponsorship of 7.500€, corresponding to 30 scholarships to undergraduate students at 250€ each, which allows covering the costs of the main seminar, or more than half of the costs of the full event.Item Reconstructing Curves from Sparse Samples on Riemannian Manifolds(The Eurographics Association and John Wiley & Sons Ltd., 2024) Marin, Diana; Maggioli, Filippo; Melzi, Simone; Ohrhallinger, Stefan; Wimmer, Michael; Hu, Ruizhen; Lefebvre, SylvainReconstructing 2D curves from sample points has long been a critical challenge in computer graphics, finding essential applications in vector graphics. The design and editing of curves on surfaces has only recently begun to receive attention, primarily relying on human assistance, and where not, limited by very strict sampling conditions. In this work, we formally improve on the state-of-the-art requirements and introduce an innovative algorithm capable of reconstructing closed curves directly on surfaces from a given sparse set of sample points. We extend and adapt a state-of-the-art planar curve reconstruction method to the realm of surfaces while dealing with the challenges arising from working on non-Euclidean domains. We demonstrate the robustness of our method by reconstructing multiple curves on various surface meshes. We explore novel potential applications of our approach, allowing for automated reconstruction of curves on Riemannian manifolds.Item Fast Rendering of Parametric Objects on Modern GPUs(The Eurographics Association, 2024) Unterguggenberger, Johannes; Lipp, Lukas; Wimmer, Michael; Kerbl, Bernhard; Schütz, Markus; Reina, Guido; Rizzi, SilvioParametric functions are an extremely efficient representation for 3D geometry, capable of compactly modelling highly complex objects. Once specified, parametric 3D objects allow for visualization at arbitrary levels of detail, at no additional memory cost, limited only by the amount of evaluated samples. However, mapping the sample evaluation to the hardware rendering pipelines of modern graphics processing units (GPUs) is not trivial. This has given rise to several specialized solutions, each targeting interactive rendering of a constrained set of parametric functions. In this paper, we propose a general method for efficient rendering of parametrically defined 3D objects. Our solution is carefully designed around modern hardware architecture. Our method adaptively analyzes, allocates and evaluates parametric function samples to produce high-quality renderings. Geometric precision can be modulated from few pixels down to sub-pixel level, enabling real-time frame rates of several 100 frames per second (FPS) for various parametric functions. We propose a dedicated level-of-detail (LOD) stage, which outputs patches of similar geometric detail to a subsequent rendering stage that uses either a hardware tessellation-based approach or performs point-based softare rasterization. Our method requires neither preprocessing nor caching, and the proposed LOD mechanism is fast enough to run each frame. Hence, our approach also lends itself to animated parametric objects. We demonstrate the benefits of our method over a state-of-the-art spherical harmonics (SH) glyph rendering method, while showing its flexibility on a range of other demanding shapes.Item Editorial(Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2025) Alliez, Pierre; Wimmer, Michael; Westermann, RüdigerItem Strokes2Surface: Recovering Curve Networks From 4D Architectural Design Sketches(The Eurographics Association and John Wiley & Sons Ltd., 2024) Rasoulzadeh, Shervin; Wimmer, Michael; Stauss, Philipp; Kovacic, Iva; Bermano, Amit H.; Kalogerakis, EvangelosWe present Strokes2Surface, an offline geometry reconstruction pipeline that recovers well-connected curve networks from imprecise 4D sketches to bridge concept design and digital modeling stages in architectural design. The input to our pipeline consists of 3D strokes' polyline vertices and their timestamps as the 4th dimension, along with additional metadata recorded throughout sketching. Inspired by architectural sketching practices, our pipeline combines a classifier and two clustering models to achieve its goal. First, with a set of extracted hand-engineered features from the sketch, the classifier recognizes the type of individual strokes between those depicting boundaries (Shape strokes) and those depicting enclosed areas (Scribble strokes). Next, the two clustering models parse strokes of each type into distinct groups, each representing an individual edge or face of the intended architectural object. Curve networks are then formed through topology recovery of consolidated Shape clusters and surfaced using Scribble clusters guiding the cycle discovery. Our evaluation is threefold: We confirm the usability of the Strokes2Surface pipeline in architectural design use cases via a user study, we validate our choice of features via statistical analysis and ablation studies on our collected dataset, and we compare our outputs against a range of reconstructions computed using alternative methods.Item Editorial(© 2024 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2024) Alliez, Pierre; Wimmer, MichaelItem Distributed Surface Reconstruction(The Eurographics Association, 2024) Marin, Diana; Komon, Patrick; Ohrhallinger, Stefan; Wimmer, Michael; Liu, Lingjie; Averkiou, MelinosRecent advancements in scanning technologies and their rise in availability have shifted the focus from reconstructing surfaces from point clouds of small areas to large, e.g., city-wide scenes, containing massive amounts of data. We adapt a surface reconstruction method to work in a distributed fashion on a high-performance cluster, reconstructing datasets with millions of vertices in seconds. We exploit the locality of the connectivity required by the reconstruction algorithm to efficiently divide-andconquer the problem of creating triangulations from very large unstructured point clouds.Item Representing and Rendering Distant Objects for Real-Time Visualization(Wimmer, June 2001) Wimmer, Michael;Computergraphik ist die Wissenschaft, die sich mit der Generierung glaubw¨urdiger Bilder besch¨aftigt. Eine der gr¨oßten Herausforderungen dabei ist, diese Bilder in ausreichender Geschwindigkeit zu erzeugen. Speziell bei der Simulation von Fahrzeugen in Stadtgebieten, bei der virtuellen Erforschung von Geb¨auden (ob noch nicht gebaute, existierende oder schon lange zerst¨orte), bei Computerspielen und vielen anderen Anwendungen ist es wichtig, daß die Bilder in fl¨ussiger Abfolge erscheinen. ¨ Ublicherweise versteht man darunter eine Bildrate von mindestens 60 Bildern pro Sekunde. Das ist das Thema der Echtzeitvisualisierung. In dieser Dissertation werden zwei Algorithmen zur beschleunigten Darstellung von großen virtuellen Szenen vorgestellt. Dabei wird bei beiden Algorithmen eine interessante Eigenschaft von vielen solchen Szenen ausgen¨utzt: Objekte, die sich weiter weg vom Betrachter befinden, machen nur einen kleinen Teil des endg¨ultigen Bildes aus, ben¨otigen aber relativ viel Rechenzeit. In dieser Dissertation wird gezeigt, wie man entfernte Objekte mit einer Komplexit¨at, die der ¨uberdeckten Bildfl¨ache und nicht ihrer eigentlichen geometrischen Komplexit¨at entspricht, repr¨asentieren und darstellen kann. Die beiden Algorithmen sind f¨ur unterschiedliche Szenarien gedacht. Die erste Methode funktioniert zur Laufzeit, braucht also keine Vorberechnung. Die zweite Methode hingegen hat einen wichtigen Vorberechnungsschritt, der bei der Darstellung sowohl die Geschwindigkeit als auch die Qualit¨at signifikant erh¨oht. Der erste Teil der Dissertation besch¨aftigt sich mit einem Algorithmus zur Darstellung von Szenen mit starker gegenseitiger Verdeckung von Objekten. Dabei kommen in mehreren Schritten bildbasierte Renderingmethoden zum Einsatz. Objekte bis zu einer bestimmten Entfernung vom Betrachter werden mit gew¨ohnlichen polygonbasierten Methoden gezeichnet. In einem weiteren pixelbasierten Schritt werden dann alle noch nicht bedeckten Pixel des Bildes identifiziert und in einem zylindrischen Zwischenspeicher f¨ur Farbwerte nachgesehen. Sollte dort kein sinnvollerWert vorhanden sein, wird die Farbe des Pixels mittels eines Blickstrahls ermittelt, sofern sich das Pixel nicht ¨uber dem Horizont befindet. Die Methode funktioniert praktisch unabh¨angig von der Anzahl der verwendeten Objekte in der Szene und erreicht eine bis zu zehnfache Beschleunigung im Vergleich zu ¨ublichen Darstellungsmethoden. Im zweiten Teil der Dissertation wird eine Datenstruktur zur getrennten Speicherung von Geometrie- und Farbinformationen f¨ur ein Objekt pr¨asentiert, geeignet f¨ur die Betrachtung aus einem bestimmten r¨aumlich abgegrenzten Bereich. Damit sollen komplexe Objekte in virtuellen Szenen insbesonders weit entfernte Objekte ersetzt werden, um eine schnellere und qualitativ bessere Darstellung dieser Objekte zu erreichen. Dabei wird das Objekt quasi mit einer Punktwolke dargestellt, deren Dichte sich nach den m¨oglichen Betrachterpositionen richtet. Das Aussehen der Punktwolke wird mittels eines Monte Carlo Verfahrens bestimmt, das eine artefaktfreie Darstellung von allen erlaubten Blickpunkten aus gestattet. Außerdem gibt diese Dissertation einen ausf¨uhrlichen ¨ Uberblick ¨uber schon publizierte Methoden im Bereich der Echtzeitvisualisierung, und enth¨alt eine Analyse ¨uber Vor- und Nachteile von bild- und punktbasierten Renderingmethoden f¨ur die Darstellung von entfernten Objekten. - Computer graphics is the art of creating believable images. The difficulty in many applications lies in doing so quickly. Architectural walkthroughs, urban simulation, computer games and many others require high-quality representation of very large models at interactive update rates. This usually means creating a new image at least 60 times a second. This is what real-time visualization is about. This thesis presents two methods to accelerate the rendering of very large virtual environments. Both algorithms exploit a common property of many such environments: distant objects usually take up a significant amount of computation time during rendering, but contribute only little to the final image. This thesis shows how to represent and render distant objects with a complexity proportional to the image area they cover, and not to their actual complexity. The algorithms are destined for different scenarios: the first is an online algorithm that carries out all computation during runtime and does not require precomputation. The second algorithm makes use of preprocessing to speed up online rendering and to improve rendering quality. The first part of the thesis shows an output-sensitive rendering algorithm for accelerating walkthroughs of large, densely occluded virtual environments using a multi-stage image-based rendering pipeline. In the first stage of the pipeline, objects within a certain distance (the near field) are rendered using the traditional graphics pipeline. In the following stages, the remainder of the scene (the far field), which consists of all pixels not yet covered by near-field geometry, is rendered by a pixel-based approach using a panoramic image cache, horizon estimation to avoid calculating sky pixels, and finally, ray casting. The time complexity of the approach does not depend on the total number of primitives in the scene. We have measured speedups of up to one order of magnitude compared to standard rendering with view-frustum culling. In the second part of the thesis, a new data structure for encoding the appearance of a geometric model as seen from a viewing region (view cell) is presented. This representation can be used in interactive or real-time visualization applications to replace complex models especially distant geometry by an impostor, maintaining high-quality rendering while cutting down on rendering time. The approach relies on an object-space sampled representation similar to a point cloud or a layered depth image, but introduces two fundamental additions to previous techniques. First, the sampling rate is controlled to provide sufficient density across all possible viewing conditions from the specified view cell. Second, a correct, antialiased representation of the plenoptic function is computed using Monte Carlo integration. The system therefore achieves high-quality rendering using a simple representation with bounded complexity. This thesis also contains a comprehensive overview of related work in the field of real-time visualization, and an in-depth discussion of the advantages and disadvantages of image-based and point-based representations for distant objects.