12 results
Search Results
Now showing 1 - 10 of 12
Item Dense 3D Gaussian Splatting Initialization for Sparse Image Data(The Eurographics Association, 2024) Seibt, Simon; Chang, Thomas Vincent Siu-Lung; von Rymon Lipinski, Bartosz ; Latoschik, Marc Erich; Liu, Lingjie; Averkiou, MelinosThis paper presents advancements in novel-view synthesis with 3D Gaussian Splatting (3DGS) using a dense and accurate SfM point cloud initialization approach. We address the challenge of achieving photorealistic renderings from sparse image data, where basic 3DGS training may result in suboptimal convergence, thus leading to visual artifacts. The proposed method enhances precision and density of initially reconstructed point clouds by refining 3D positions and extrapolating additional points, even for difficult image regions, e.g. with repeating patterns and suboptimal visual coverage. Our contributions focus on improving ''Dense Feature Matching for Structure-from-Motion'' (DFM4SfM) based on a homographic decomposition of the image space to support 3DGS training: First, a grid-based feature detection method is introduced for DFM4SfM to ensure a welldistributed 3D Gaussian initialization uniformly over all depth planes. Second, the SfM feature matching is complemented by a geometric plausibility check, priming the homography estimation and thereby improving the initial placement of 3D Gaussians. Experimental results on the NeRF-LLFF dataset demonstrate that this approach achieves superior qualitative and quantitative results, even for fewer views, and the potential for a significantly accelerated 3DGS training with faster convergence.Item Modeling and Enhancement of LiDAR Point Clouds from Natural Scenarios(The Eurographics Association, 2022) Collado, José Antonio; López, Alfonso; Jiménez-Pérez, J. Roberto; Ortega, Lidia M.; Feito, Francisco R.; Jurado, Juan Manuel; Sauvage, Basile; Hasic-Telalovic, JasminkaThe generation of realistic natural scenarios is a longstanding and ongoing challenge in Computer Graphics. A common source of real-environmental scenarios is open point cloud datasets acquired by LiDAR (Laser Imaging Detection and Ranging) devices. However, these data have low density and are not able to provide sufficiently detailed environments. In this study, we propose a method to reconstruct real-world environments based on data acquired from LiDAR devices that overcome this limitation and generate rich environments, including ground and high vegetation. Additionally, our proposal segments the original data to distinguish among different kinds of trees. The results show that the method is capable of generating realistic environments with the chosen density and including specimens of each of the identified tree types.Item Enhanced Reconstruction of Architectural Wall Surfaces for 3D Building Models(The Eurographics Association, 2019) Michailidis, Georgios-Tsampikos; Pajarola, Renato; Fusiello, Andrea and Bimber, OliverThe reconstruction of architectural structures from 3D building models is a challenging task and a lot of research has been done in recent years. However, most of this work is focused mainly on reconstructing accurately the architectural shape of interiors rather than the fine architectural details, such as the wall elements (e.g. windows and doors). We focus specifically on this problem and propose a method that extends current solutions to reconstruct accurately severely occluded wall surfaces.Item Parameter-Free and Improved Connectivity for Point Clouds(The Eurographics Association, 2023) Marin, Diana; Ohrhallinger, Stefan; Wimmer, Michael; Singh, Gurprit; Chu, Mengyu (Rachel)Determining connectivity in unstructured point clouds is a long-standing problem that is still not addressed satisfactorily. In this poster, we propose an extension to the proximity graph introduced in [MOW22] to three-dimensional models. We use the spheres-of-influence (SIG) proximity graph restricted to the 3D Delaunay graph to compute connectivity between points. Our approach shows a better encoding of the connectivity in relation to the ground truth than the k-nearest neighborhood (kNN) for a wide range of k values, and additionally, it is parameter-free. Our result for this fundamental task offers potential for many applications relying on kNN, e.g., improvements in normal estimation, surface reconstruction, motion planning, simulations, and many more.Item Raw Point Cloud Deferred Shading Through Screen Space Pyramidal Operators(The Eurographics Association, 2018) Bouchiba, Hassan; Deschaud, Jean-Emmanuel; Goulette, François; Diamanti, Olga and Vaxman, AmirWe present a novel real-time raw point cloud rendering algorithm based on efficient screen-space pyramidal operators. Our method is based on a pyramidal occlusion-based hidden point removal operator followed by a pyramidal reconstruction by the pull push algorithm. Then a new pyramidal smooth normals estimator enables subsequent deferred shading. We demonstrate on various real-world complex objects and scenes that our method achieves better visual results and is one order of magnitude more efficient comparing to state of the art algorithms.Item MEPP2: A Generic Platform for Processing 3D Meshes and Point Clouds(The Eurographics Association, 2020) Vidal, Vincent; Lombardi, Eric; Tola, Martial; Dupont, Florent; Lavoué, Guillaume; Wilkie, Alexander and Banterle, FrancescoIn this paper, we present MEPP2, an open-source C++ software development kit (SDK) for processing and visualizing 3D surface meshes and point clouds. It provides both an application programming interface (API) for creating new processing filters and a graphical user interface (GUI) that facilitates the integration of new filters as plugins. Static and dynamic 3D meshes and point clouds with appearance-related attributes (color, texture information, normal) are supported. The strength of the platform is to be generic programming oriented. It offers an abstraction layer, based on C++ Concepts, that provides interoperability over several third party mesh and point cloud data structures, such as OpenMesh, CGAL, and PCL. Generic code can be run on all data structures implementing the required concepts, which allows for performance and memory footprint comparison. Our platform also permits to create complex processing pipelines gathering idiosyncratic functionalities of the different libraries. We provide examples of such applications. MEPP2 runs on Windows, Linux & Mac OS X and is intended for engineers, researchers, but also students thanks to simple use, facilitated by the proposed architecture and extensive documentation.Item A Survey on Data-driven Dictionary-based Methods for 3D Modeling(The Eurographics Association and John Wiley & Sons Ltd., 2018) Lescoat, Thibault; Ovsjanikov, Maks; Memari, Pooran; Thiery, Jean-Marc; Boubekeur, Tamy; Hildebrandt, Klaus and Theobalt, ChristianDictionaries are very useful objects for data analysis, as they enable a compact representation of large sets of objects through the combination of atoms. Dictionary-based techniques have also particularly benefited from the recent advances in machine learning, which has allowed for data-driven algorithms to take advantage of the redundancy in the input dataset and discover relations between objects without human supervision or hard-coded rules. Despite the success of dictionary-based techniques on a wide range of tasks in geometric modeling and geometry processing, the literature is missing a principled state-of-the-art of the current knowledge in this field. To fill this gap, we provide in this survey an overview of data-driven dictionary-based methods in geometric modeling. We structure our discussion by application domain: surface reconstruction, compression, and synthesis. Contrary to previous surveys, we place special emphasis on dictionary-based methods suitable for 3D data synthesis, with applications in geometric modeling and design. Our ultimate goal is to enlight the fact that these techniques can be used to combine the data-driven paradigm with design intent to synthesize new plausible objects with minimal human intervention. This is the main motivation to restrict the scope of the present survey to techniques handling point clouds and meshes, making use of dictionaries whose definition depends on the input data, and enabling shape reconstruction or synthesis through the combination of atoms.Item 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 Recent Trends in 3D Reconstruction of General Non-Rigid Scenes(The Eurographics Association and John Wiley & Sons Ltd., 2024) Yunus, Raza; Lenssen, Jan Eric; Niemeyer, Michael; Liao, Yiyi; Rupprecht, Christian; Theobalt, Christian; Pons-Moll, Gerard; Huang, Jia-Bin; Golyanik, Vladislav; Ilg, Eddy; Aristidou, Andreas; Macdonnell, RachelReconstructing models of the real world, including 3D geometry, appearance, and motion of real scenes, is essential for computer graphics and computer vision. It enables the synthesizing of photorealistic novel views, useful for the movie industry and AR/VR applications. It also facilitates the content creation necessary in computer games and AR/VR by avoiding laborious manual design processes. Further, such models are fundamental for intelligent computing systems that need to interpret real-world scenes and actions to act and interact safely with the human world. Notably, the world surrounding us is dynamic, and reconstructing models of dynamic, non-rigidly moving scenes is a severely underconstrained and challenging problem. This state-of-the-art report (STAR) offers the reader a comprehensive summary of state-of-the-art techniques with monocular and multi-view inputs such as data from RGB and RGB-D sensors, among others, conveying an understanding of different approaches, their potential applications, and promising further research directions. The report covers 3D reconstruction of general non-rigid scenes and further addresses the techniques for scene decomposition, editing and controlling, and generalizable and generative modeling. More specifically, we first review the common and fundamental concepts necessary to understand and navigate the field and then discuss the state-of-the-art techniques by reviewing recent approaches that use traditional and machine-learning-based neural representations, including a discussion on the newly enabled applications. The STAR is concluded with a discussion of the remaining limitations and open challenges.Item SIG-based Curve Reconstruction(The Eurographics Association, 2022) Marin, Diana; Ohrhallinger, Stefan; Wimmer, Michael; Sauvage, Basile; Hasic-Telalovic, JasminkaWe introduce a new method to compute the shape of an unstructured set of two-dimensional points. The algorithm exploits the to-date rarely used proximity-based graph called spheres-of-influence graph (SIG). We filter edges from the Delaunay triangulation belonging to the SIG as an initial graph and apply some additional processing plus elements from the Connect2D algorithm. This combination already shows improvements in curve reconstruction, yielding the best reconstruction accuracy compared to state-of-the-art algorithms from a recent comprehensive benchmark, and offers potential of further improvements.