EG 2019 - Posters

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2632749

Browse

Now showing 1 - 17 of 17

3D Mesh Description Using ''Subdivided Shape-Curvature-Graphs''
(The Eurographics Association, 2019) Beguet, Florian; Guise, Jacques De; Schmittbuhl, Matthieu; Mari, Jean-Luc; Cresson, Thierry; Fusiello, Andrea and Bimber, Oliver
This paper presents a shape descriptor for 3D meshes using a graph to represent a polyhedral mesh which is then used to extract patterns from the shape. The use of Subdivided Shape-Curvature-Graphs makes it possible to not only recognize the similarities of mesh details but also determine the self-similarity of local portions of the object by adding topological information to the graph. The proposed method divides the mesh into 8 categories of patches using the discrete curvatures. These patches are cleaned; afterwards, to add topological information, a new "segmentation" patch is added. Finally, an approach is developed to extract and compare the subgraphs and thus be able to obtain the self-similarity of local parts of the mesh.
Adaptive Frameless Rendering with NVIDIA OptiX
(The Eurographics Association, 2019) Hsiao, Chung-Che; Watson, Benjamin; Fusiello, Andrea and Bimber, Oliver
We implement adaptive frameless rendering (AFR) on NVIDIA OptiX, a real-time ray tracing API taking advantage of NVIDIA GPUs including their latest RTX functionality. OptiX is a parallel system that sits on top of NVIDIA's better-known CUDA API. AFR has sampling and reconstruction processes that use information distributed across both space and time, aiming to generate low-latency updates. Previous AFR implementations were sequential prototypes. Our parallel prototype is allowing us to confront several unique challenges, including closed loop control of both sampling and reconstruction, and load balancing between CPU and GPU.
Assembly Retrieval Results Inspection in Immersive Environment
(The Eurographics Association, 2019) Lupinetti, Katia; Bonino, Brigida; Giannini, Franca; monti, marina; Fusiello, Andrea and Bimber, Oliver
This poster presents a research aimed at supporting the browsing through the results of an assembly retrieval system by exploiting Virtual Reality technologies. To support the users' understanding during the assessing of the similarities of 3D assembly models, the proposed system exploits the three-dimensionality of the space to locate the retrieved models distributing them according to their dissimilarity to the model used as query. It also allows the users to interact with assemblies through voice and gesture commands, which resemble gestures well-established in touch user interfaces. Through them, users can see correspondences between assemblies, disassemble and re-assemble 3D digital models, such that it is possible a better inspection of the assembly components that is the first step for the development of systems allowing for their modifications and combinations.
Can we Invert a Local Reflectance Model From a Single Specular Highlight with Known Scene Geometry and Camera Pose?
(The Eurographics Association, 2019) Hadj-Said, Souheil; Tamaazousti, Mohamed; Bartoli, Adrien; Fusiello, Andrea and Bimber, Oliver
Recovering the scene's illumination from images is a crucial step in Augmented and Diminished Reality. We present an experimental investigation to assess the well-posedness of this problem (i) using a known scene geometry and camera pose and (ii) assuming that a local reflectance model such as Blinn-Phong's holds. Based on results on synthetic and real data, we establish two major observations. First, the problem of retrieving the full local reflectance model's parameters and light source position from the original image is ill-posed. Second, the specular parameters including the light source position can be stably estimated from the image's specular component using a single specular highlight region.
D.A.V.E: A Prototype for Automatic Environment Decoration
(The Eurographics Association, 2019) Glover, Callum James; Anderson, Eike Falk; Fusiello, Andrea and Bimber, Oliver
To fully immerse players in video games, elements of the game world must form a rich, coherent and believable universe, which is time consuming and expensive to achieve manually. We propose an artists' tool for Autodesk Maya to aid environment decoration, allowing artists to focus on the more important elements of the worlds they create.
The Effects of Adaptive Synchronization on Performance and Experience in Gameplay
(The Eurographics Association, 2019) Watson, Benjamin; Gavane, Ajinkya; Shrivastava, Rachit; Fusiello, Andrea and Bimber, Oliver
As graphics (GPU) hardware has improved, fixed refresh rate displays became a significant throttle on graphics performance. GPU and display manufacturers therefore introduced adaptive synchronization (Async), which allows displays to adaptively synchronize to GPUs, avoiding rendering stalls and improving frame rate mean and variation. This research is a first experimental examination of the effects of Async on the experience of dedicated (but not professional) gamers. Participants played a first-person shooter (FPS) game, both with Async on and with Async off. After each game session, we assessed participant emotional state and gaming performance. We learned that at least for this popular FPS, Async can improve gaming performance, and may also benefit experience. We also found that Async has intriguing relationships to game familiarity and years of gameplay that merit additional investigation. Further research should examine these relationships, as well as Async's effects in systems with higher frame rates.
Enhanced Reconstruction of Architectural Wall Surfaces for 3D Building Models
(The Eurographics Association, 2019) Michailidis, Georgios-Tsampikos; Pajarola, Renato; Fusiello, Andrea and Bimber, Oliver
The 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.
EUROGRAPHICS 2019: Posters Frontmatter
(Eurographics Association, 2019) Fusiello, Andrea; Bimber, Oliver; Fusiello, Andrea and Bimber, Oliver
Flexible Type: Methods and Applications of Modifying Glyph's Horizontal and Vertical Weight
(The Eurographics Association, 2019) Kumawat, Nirmal; dhanuka, praveen kumar; Fusiello, Andrea and Bimber, Oliver
Graphic designers create logos or artworks by using various tools such as Adobe Illustrator, InDesign etc. Many times, designers face a major problem where they want to change the visual appearance of the text to fit the design in the current context or to make the design look better, but text editing options provided today are very limiting to the user's creativity. The designers get around this by converting text to outlines and then modifying each glyph like a separate graphic. This leads to text no longer being live (essentially unlinked) and the edits for each glyph can be time consuming. The poster presents methods for modifying glyph's horizontal and vertical weight. Later, the poster aims to provide the application of such modification to generate multiple styles by modifying glyph's overall Weight, Width, CapHeight, xHeight, height of Ascender and Descender etc.
Multi-Scale Point Cloud Analysis
(The Eurographics Association, 2019) Lejemble, Thibault; Mura, Claudio; Barthe, Loïc; Mellado, Nicolas; Fusiello, Andrea and Bimber, Oliver
Surfaces sampled with point clouds often exhibit multi-scale properties due to the high variation between their feature size. Traditional shape analysis techniques usually rely on geometric descriptors able to characterize a point and its close neighborhood at multiple scale using smoothing kernels of varying radii. We propose to add a spatial regularization to these point-wise descriptors in two different ways. The first groups similar points in regions that are structured in a hierarchical graph. The graph is then simplified and processed to extract pertinent regions. The second performs a spatial gradient descent in order to highlight stable parts of the surface. We show two experiments focusing on planar and anisotropic feature areas respectively.
A Projection Mapping System onto a Human Body for Medical Applications
(The Eurographics Association, 2019) Fukuhara, Ryo; Kaneda, Kazufumi; Tamaki, Toru; Raytchev, Bisser; Higaki, Toru; Nishimoto, Soh; Sotsuka, Yohei; Fusiello, Andrea and Bimber, Oliver
In breast reconstructive surgery where patient's abdominal fat and blood vessels are transplanted to the breast, it is very important to identify the course of the blood vessels inside the abdomen. In this paper, we propose a system for projecting blood vessels extracted from computer tomography angiography (CTA) on a patient's abdominal surface to support the breast reconstructive surgery. The proposed system detects the position and orientation of a projector automatically using an image captured by a camera mounted with the projector and is able to project the exact course of the blood vessels onto an abdominal skin from an arbitrary direction. An experiment using an abdominal model fabricated from patient's CTA data with a 3D printer demonstrates the usefulness of the proposed system.
Towards Point-based Facial Movement Simulation
(The Eurographics Association, 2019) Uhlmann, Tom; Brunnett, Guido; Fusiello, Andrea and Bimber, Oliver
Lifelike animated characters are hard to create and involve extensive manual effort during generation of the geometry, adding a rig to the model, and creating the actual movements of limbs and tissue. Blendshapes is the leading technique regarding facial animations. This very simple mathematical model can be computed efficiently, thus it is suited for real time visualization. On the other hand it is hard to control, requires a skilled animator, and is still very error prone. Point-based simulation techniques became increasingly popular in recent years for animation of elastic surfaces, but have barely been used for facial animation. We argue, that this kind of technique is much more suited for simulation and animation of the non-rigid deformations of facial tissue. We build our proposal on a meshless finite elements technique, which has already been used successfully for the elastic simulation of surface models in real time and describe extensions to the approach so it can be applied for facial animation.
Towards the Fitting of Parametric 2D Sketches and 3D CAD Models to Point Clouds of Digitized Assemblies for Reverse Engineering
(The Eurographics Association, 2019) SHAH, Ghazanfar Ali; Giannini, Franca; monti, marina; Polette, Arnaud; PERNOT, Jean-Philippe; Fusiello, Andrea and Bimber, Oliver
Following commonly used reverse engineering techniques, it is very difficult to reconstruct editable CAD parts or assemblies that can later be used and modified in the Product Development Process (PDP). Traditional methods follow a sequential time-consuming patch-by-patch reconstruction strategy with cumbersome procedures in which designers usually have to face many issues (e.g. decomposition in patches, trimming and connection of the patches), and generally producing ''dead'' models that cannot be later modified as needed. This paper describes a new reverse engineering technique that allows fitting of parametric CAD parts or an assembly to a reference point cloud to be reconstructed. The proposed fitting method can also be applied to 2D configurations to adapt a parametric 2D sketch to a 2D point cloud section. The idea is to use a parametric CAD model or a parametric 2D sketch in an optimization algorithm allowing their perfect fitting into the point cloud of a scanned mechanical assembly for efficient reconstruction of good quality CAD models. Some well-known algorithms like ICP are also used to derive the orientation and position of pre-arranged CAD model or 2D sketch throughout the fitting process. Both global and local fittings are possible. The consistency of the CAD models is ensured by a modeler which updates the CAD models or 2D sketch according to the iterative dimensional modifications. The evaluation of the proposed approach is performed using as-scanned virtually generated point clouds which incorporate several artifacts that would appear using a real scanner. This technique allows for the comparison between the dimensions of the fitted parts and the ones of the parts used to generate the point clouds.
Visual-auditory Representation and Analysis of Molecular Scalar Fields
(The Eurographics Association, 2019) Malikova, Evgeniya; Adzhiev, Valery; Fryazinov, Oleg; Pasko, Alexander; Fusiello, Andrea and Bimber, Oliver
The work deals with a visual-auditory representation and an analysis of static and dynamic continuous scalar fields.We propose a general approach and give examples of dynamic and static objects representations related to molecular data simulations. We describe the practical application and demonstrate how the approach may help to track geometrical features.
Visualization of Large Point Cloud in Unity
(The Eurographics Association, 2019) Santana Núñez, José Miguel; Trujillo, Agustin; Ortega, Sebastián; Fusiello, Andrea and Bimber, Oliver
Large point cloud rendering has become a very relevant topic on 3D graphics as scanners and other sources of 3D point data are nowadays available to companies and the general public. In this project, we propose an implementation of a point cloud viewer, designed for the full-detail visualization of virtually unlimited point clouds for their inspection on short ranges. This work presents the data structure and the LoD technique to achieve a real-time rendering of the model, making emphasis on the details of an initial prototype based on Unity.
VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
(The Eurographics Association, 2019) Honda, Shion; Fusiello, Andrea and Bimber, Oliver
Generating a virtual try-on image from in-shop clothing images and a model person's snapshot is a challenging task because the human body and clothes have high flexibility in their shapes. In this paper, we develop a Virtual Try-on Generative Adversarial Network (VITON-GAN), that generates virtual try-on images using images of in-shop clothing and a model person. This method enhances the quality of the generated image when occlusion is present in a model person's image (e.g., arms crossed in front of the clothes) by adding an adversarial mechanism in the training pipeline.
Voxelizing Light-Field Recordings
(The Eurographics Association, 2019) Schedl, David; Kurmi, Indrajit; Bimber, Oliver; Fusiello, Andrea and Bimber, Oliver
Light fields are an emerging image-based technique that support free viewpoint navigation of recorded scenes as demanded in several recent applications (e.g., Virtual Reality). Pure image-based representations, however quickly become inefficient, as a large number of images are required to be captured, stored, and processed. Geometric scene representations require less storage and are more efficient to render. Geometry reconstruction, however, is unreliable and might fail for complex scene parts. Furthermore, view-dependent effects that are preserved with light fields are lost in pure geometry-based techniques. Therefore, we propose a hybrid representation and rendering scheme for recorded dense light fields: we extract isotropic scene regions and represent them by voxels, while the remaining areas are represented as sparse light field. In comparison to dense light fields, storage demands are reduced while visual quality is sustained.

Browse

Browsing EG 2019 - Posters by Title

Results Per Page

Sort Options