Search

We present a machine learning approach for efficiently computing order independent transparency (OIT). Our method is fast, requires a small constant amount of memory (depends only on the screen resolution and not on the number of triangles or transparent layers), is more accurate as compared to previous approximate methods, works for every scene without setup and is portable to all platforms running even with commodity GPUs. Our method requires a rendering pass to extract all features that are subsequently used to predict the overall OIT pixel color with a pre-trained neural network. We provide a comparative experimental evaluation and shader source code of all methods for reproduction of the experiments.

Additive manufacturing is a process that has facilitated the cost effective production of complicated designs. Objects fabricated via additive manufacturing technologies often suffer from dimensional accuracy issues and other part specific problems such as thin part robustness, overhang geometries that may collapse, support structures that cannot be removed, engraved and embossed details that are indistinguishable. In this work we present an approach to predict the dimensional accuracy per vertex and per part. Furthermore, we provide a framework for estimating the probability that a model is fabricated correctly via an additive manufacturing technology for a specific application. This framework can be applied to several 3D printing technologies and applications. In the context of this paper, a thorough experimental evaluation is presented for binder jetting technology and applications., Comment: This version has been published in the Rapid Prototyping Journal (2023)

In computer graphics, animation compression is essential for efficient storage, streaming and reproduction of animated meshes. Previous work has presented efficient techniques for compression by deriving skinning transformations and weights using clustering of vertices based on geometric features of vertices over time. In this work we present a novel approach that assigns vertices to bone-influenced clusters and derives weights using deep learning through a training set that consists of pairs of vertex trajectories (temporal vertex sequences) and the corresponding weights drawn from fully rigged animated characters. The approximation error of the resulting linear blend skinning scheme is significantly lower than the error of competent previous methods by producing at the same time a minimal number of bones. Furthermore, the optimal set of transformation and vertices is derived in fewer iterations due to the better initial positioning in the multidimensional variable space. Our method requires no parameters to be determined or tuned by the user during the entire process of compressing a mesh animation sequence., Comment: CGI 2021, LNCS Proceedings, to appear. For video and presentation and other info please see http://www.cgrg.cs.uoi.gr/single-publication?ID=48

Texturing is a fundamental process in computer graphics. Texture is leveraged to enhance the visualization outcome for a 3D scene. In many cases a texture image cannot cover a large 3D model surface because of its small resolution. Conventional techniques like repeating, mirror repeating or clamp to edge do not yield visually acceptable results. Deep learning based texture synthesis has proven to be very effective in such cases. All deep texture synthesis methods trying to create larger resolution textures are limited in terms of GPU memory resources. In this paper, we propose a novel approach to example-based texture synthesis by using a robust deep learning process for creating tiles of arbitrary resolutions that resemble the structural components of an input texture. In this manner, our method is firstly much less memory limited owing to the fact that a new texture tile of small size is synthesized and merged with the original texture and secondly can easily produce missing parts of a large texture.

Additive manufacturing technologies are positioned to provide an unprecedented innovative transformation in how products are designed and manufactured. Due to differences in the technical specifications of AM technologies, the final fabricated parts can vary significantly from the original CAD models, therefore raising issues regarding accuracy, surface finish, robustness, mechanical properties, functional and geometrical constraints. Various researchers have studied the correlation between AM technologies and design rules. In this work we propose a novel approach to assessing the capability of a 3D model to be printed successfully (a.k.a printability) on a specific AM machine. This is utilized by taking into consideration the model mesh complexity and certain part characteristics. A printability score is derived for a model in reference to a specific 3D printing technology, expressing the probability of obtaining a robust and accurate end result for 3D printing on a specific AM machine. The printability score can be used either to determine which 3D technology is more suitable for manufacturing a specific model or as a guide to redesign the model to ensure printability. We verify this framework by conducting 3D printing experiments for benchmark models which are printed on three AM machines employing different technologies: Fused Deposition Modeling (FDM), Binder Jetting (3DP), and Material Jetting (Polyjet)., Comment: To appear in Computer-Aided Design and Applications Journal (http://www.cad-journal.net/open-access.html): I. Fudos, M. Ntousia, V. Stamati, P. Charalampous, T. Kontodina, I. Kostavelis, D. Tzovaras and L. Bilalis. A Characterization of 3D Printability. Accepted, Computer Aided Design and Applications, 2020

In this paper, we are concerned with geometric constraint solvers, i.e., with programs that find one or more solutions of a geometric constraint problem. If no solution exists, the solver is expected to announce that no solution has been found. Owing to the complexity, type or difficulty of a constraint problem, it is possible that the solver does not find a solution even though one may exist. Thus, there may be false negatives, but there should never be false positives. Intuitively, the ability to find solutions can be considered a measure of solver's competence. We consider static constraint problems and their solvers. We do not consider dynamic constraint solvers, also known as dynamic geometry programs, in which specific geometric elements are moved, interactively or along prescribed trajectories, while continually maintaining all stipulated constraints. However, if we have a solver for static constraint problems that is sufficiently fast and competent, we can build a dynamic geometry program from it by solving the static problem for a sufficiently dense sampling of the trajectory of the moving element(s). The work we survey has its roots in applications, especially in mechanical computer-aided design (MCAD). The constraint solvers used in MCAD took a quantum leap in the 1990s. These approaches solve a geometric constraint problem by an initial, graph-based structural analysis that extracts generic subproblems and determines how they would combine to form a complete solution. These subproblems are then handed to an algebraic solver that solves the specific instances of the generic subproblems and combines them., Comment: This work was accepted to appear as a chapter, pending minor revision, to the "Handbook of Geometric Constraints Principles", edited by Meera Sitharam, Audrey St.John and Jessica Sidman, Mathematics series, CRC press (Taylor and Francis group). To appear in 2017. Universitat Politecnica de Catalunya, Research Report: http://hdl.handle.net/2117/91041