EG2022

Permanent URI for this community

https://diglib.eg.org/handle/10.2312/2633163

Browse

Now showing 1 - 20 of 66

SIG-based Curve Reconstruction
(The Eurographics Association, 2022) Marin, Diana; Ohrhallinger, Stefan; Wimmer, Michael; Sauvage, Basile; Hasic-Telalovic, Jasminka
We 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.
Robust Sample Budget Allocation for MIS
(The Eurographics Association, 2022) Szirmay-Kalos, László; Sbert, Mateu; Pelechano, Nuria; Vanderhaeghe, David
Multiple Importance Sampling (MIS) combines several sampling techniques. Its weighting scheme depends on how many samples are generated with each particular method. This paper examines the optimal determination of the number of samples allocated to each of the combined techniques taking into account that this decision can depend only on a relatively small number of previous samples. The proposed method is demonstrated with the combination of BRDF sampling and Light source sampling, and we show that due to its robustness, it can outperform the theoretically more accurate approaches.
Safeguarding our Dance Cultural Heritage
(The Eurographics Association, 2022) Aristidou, Andreas; Chalmers, Alan; Chrysanthou, Yiorgos; Loscos, Celine; Multon, Franck; Parkins, J. E.; Sarupuri, Bhuvan; Stavrakis, Efstathios; Hahmann, Stefanie; Patow, Gustavo A.
Folk dancing is a key aspect of intangible cultural heritage that often reflects the socio-cultural and political influences prevailing in different periods and nations; each dance produces a meaning, a story with the help of music, costumes and dance moves. It has been transmitted from generation to generation, and to different countries, mainly due to movements of people carrying and disseminating their civilization. However, folk dancing, amongst other intangible heritage, is at high risk of disappearing due to wars, the moving of populations, economic crises, modernization, but most importantly, because these fragile creations have been modified over time through the process of collective recreation, and/or changes in the way of life. In this tutorial, we show how the European Project, SCHEDAR, exploited emerging technologies to digitize, analyze, and holistically document our intangible heritage creations, that is a critical necessity for the preservation and the continuity of our identity as Europeans.
Quick Cone Map Generation on the GPU
(The Eurographics Association, 2022) Valasek, Gábor; Bán, Róbert; Pelechano, Nuria; Vanderhaeghe, David
We propose an efficient conservative cone map generation algorithm that has T(N^2 logN) complexity for textures of dimension N ×N in contrast to the T(N^4) complexity of brute-force approaches. This is achieved by using a maximum mip texture of a heightmap to process all texels during the search for cone apertures, resulting in real-time generation times. Furthermore, we show that discarding already visited regions of neighboring mip texels widens the obtained cones considerably while still being conservative. Finally, we present a method to increase cone aperture tangents further at the expense of conservativeness. We compare our methods to brute-force and relaxed cone maps in generation and rendering performance.
EUROGRAPHICS 2022: Posters Frontmatter
(The Eurographics Association, 2022) Sauvage, Basile; Hasic-Telalovic, Jasminka; Sauvage, Basile; Hasic-Telalovic, Jasminka
Digital Matte Painting - An Effective Undergraduate Assignment
(The Eurographics Association, 2022) Redford, Adam; Anderson, Eike Falk; Bourdin, Jean-Jacques; Paquette, Eric
This paper presents an effective digital matte painting assignment from a course delivered as part of an undergraduate degree programme in visual effects. The assignment involves the creation of a final 3D shot from an initial 2D image, using various 2D image manipulation tools and appropriate 2.5D image projection techniques.
Neural Fields in Visual Computing and Beyond
(The Eurographics Association and John Wiley & Sons Ltd., 2022) Xie, Yiheng; Takikawa, Towaki; Saito, Shunsuke; Litany, Or; Yan, Shiqin; Khan, Numair; Tombari, Federico; Tompkin, James; Sitzmann, Vincent; Sridhar, Srinath; Meneveaux, Daniel; Patanè, Giuseppe
Recent advances in machine learning have led to increased interest in solving visual computing problems using methods that employ coordinate-based neural networks. These methods, which we call neural fields, parameterize physical properties of scenes or objects across space and time. They have seen widespread success in problems such as 3D shape and image synthesis, animation of human bodies, 3D reconstruction, and pose estimation. Rapid progress has led to numerous papers, but a consolidation of the discovered knowledge has not yet emerged. We provide context, mathematical grounding, and a review of over 250 papers in the literature on neural fields. In Part I, we focus on neural field techniques by identifying common components of neural field methods, including different conditioning, representation, forward map, architecture, and manipulation methods. In Part II, we focus on applications of neural fields to different problems in visual computing, and beyond (e.g., robotics, audio). Our review shows the breadth of topics already covered in visual computing, both historically and in current incarnations, and highlights the improved quality, flexibility, and capability brought by neural field methods. Finally, we present a companion website that acts as a living database that can be continually updated by the community.
RGB-D Neural Radiance Fields: Local Sampling for Faster Training
(The Eurographics Association, 2022) Dey, Arnab; Comport, Andrew I.; Sauvage, Basile; Hasic-Telalovic, Jasminka
Learning a 3D representation of a scene has been a challenging problem for decades in computer vision. Recent advancements in implicit neural representation from images using neural radiance fields(NeRF) have shown promising results. Some of the limitations of previous NeRF based methods include longer training time, and inaccurate underlying geometry. The proposed method takes advantage of RGB-D data to reduce training time by leveraging depth sensing to improve local sampling. This paper proposes a depth-guided local sampling strategy and a smaller neural network architecture to achieve faster training time without compromising quality.
3D Human Shape and Pose from a Single Depth Image with Deep Dense Correspondence Enabled Model Fitting
(The Eurographics Association, 2022) Wang, Xiaofang; Boukhayma, Adnane; Prévost, Stéphanie; Desjardin, Eric; Loscos, Celine; Multon, Franck; Sauvage, Basile; Hasic-Telalovic, Jasminka
We propose a two-stage hybrid method, with no initialization, for 3D human shape and pose estimation from a single depth image, combining the benefits of deep learning and optimization. First, a convolutional neural network predicts pixel-wise dense semantic correspondences to a template geometry, in the form of body part segmentation labels and normalized canonical geometry vertex coordinates. Using these two outputs, pixel-to-vertex correspondences are computed in a six-dimensional embedding of the template geometry through nearest neighbor. Second, a parametric shape model (SMPL) is fitted to the depth data by minimizing vertex distances to the input. Extensive evaluation on both real and synthetic human shape in motion datasets shows that our method yields quantitatively and qualitatively satisfactory results and state-of-the-art reconstruction errors.
Fitness of General-Purpose Monocular Depth Estimation Architectures for Transparent Structures
(The Eurographics Association, 2022) Wirth, Tristan; Jamili, Aria; Buelow, Max von; Knauthe, Volker; Guthe, Stefan; Pelechano, Nuria; Vanderhaeghe, David
Due to material properties, monocular depth estimation of transparent structures is inherently challenging. Recent advances leverage additional knowledge that is not available in all contexts, i.e., known shape or depth information from a sensor. General-purpose machine learning models, that do not utilize such additional knowledge, have not yet been explicitly evaluated regarding their performance on transparent structures. In this work, we show that these models show poor performance on the depth estimation of transparent structures. However, fine-tuning on suitable data sets, such as ClearGrasp, increases their estimation performance on the task at hand. Our evaluations show that high performance on general-purpose benchmarks translates well into performance on transparent objects after fine-tuning. Furthermore, our analysis suggests, that state-of-theart high-performing models are not able to capture a high grade of detail from both the image foreground and background at the same time. This finding shows the demand for a combination of existing models to further enhance depth estimation quality.
Transfer Textures for Fast Precomputed Radiance Transfer
(The Eurographics Association, 2022) Dhawal, Sirikonda; Kt, Aakash; Narayanan, P. J.; Sauvage, Basile; Hasic-Telalovic, Jasminka
Precomputed Radiance Transfer (PRT) can achieve high-quality renders of glossy materials at real-time framerates. PRT involves precomputing a k-dimensional transfer vector or a k×k- matrix of Spherical Harmonic (SH) coefficients at specific points for a scene depending on whether the material is diffuse or glossy respectively. Most prior art precomputes values at vertices of the mesh and interpolates color for interior points. They require finer mesh tessellations for high-quality renders. In this work, we introduce transfer textures for decoupling mesh resolution from transfer storage and sampling specifically benefiting the glossy renders. Dense sampling of the transfer is possible on the fragment shader while rendering with the use of transfer textures for both diffuse as well as glossy materials, even with a low tessellation. This simultaneously provides high render quality and frame rates.
An Improved Triangle Encoding Scheme for Cached Tessellation
(The Eurographics Association, 2022) Kerbl, Bernhard; Horváth, Linus; Cornel, Daniel; Wimmer, Michael; Pelechano, Nuria; Vanderhaeghe, David
With the recent advances in real-time rendering that were achieved by embracing software rasterization, the interest in alternative solutions for other fixed-function pipeline stages rises. In this paper, we revisit a recently presented software approach for cached tessellation, which compactly encodes and stores triangles in GPU memory. While the proposed technique is both efficient and versatile, we show that the original encoding is suboptimal and provide an alternative scheme that acts as a drop-in replacement. As shown in our evaluation, the proposed modifications can yield performance gains of 40% and more.
SOFA: an Open-source Solution for Physics Simulation
(The Eurographics Association, 2022) Talbot, Hugo; Hahmann, Stefanie; Patow, Gustavo A.
SOFA is an open-source framework for interactive physics simulation and is being developed for more than 16 years. Today, SOFA benefits from a large international community made up of research centers and companies. The SOFA core has a LGPL license (permissive and non-contaminating) fostering the development of prototypes and products under any commercial license. This half-day EG22 tutorial proposes an introduction on biomechanical simulation with SOFA, covering the main principles of a simulation and its lifecycle. Then, a hands-on session will bring the basis to build your own simulation for medical/VR/AR/robotics applications!
AvatarGo: Plug and Play self-avatars for VR
(The Eurographics Association, 2022) Ponton, Jose Luis; Monclús, Eva; Pelechano, Nuria; Pelechano, Nuria; Vanderhaeghe, David
The use of self-avatars in a VR application can enhance presence and embodiment which leads to a better user experience. In collaborative VR it also facilitates non-verbal communication. Currently it is possible to track a few body parts with cheap trackers and then apply IK methods to animate a character. However, the correspondence between trackers and avatar joints is typically fixed ad-hoc, which is enough to animate the avatar, but causes noticeable mismatches between the user's body pose and the avatar. In this paper we present a fast and easy to set up system to compute exact offset values, unique for each user, which leads to improvements in avatar movement. Our user study shows that the Sense of Embodiment increased significantly when using exact offsets as opposed to fixed ones. We also allowed the users to see a semitransparent avatar overlaid with their real body to objectively evaluate the quality of the avatar movement with our technique.
Simple Techniques for a Novel Human Body Pose Optimisation Using Differentiable Inverse Rendering
(The Eurographics Association, 2022) Battogtokh, Munkhtulga; Borgo, Rita; Pelechano, Nuria; Vanderhaeghe, David
Human body 3D reconstruction has a wide range of applications including 3D-printing, art, games, and even technical sport analysis. This is a challenging problem due to 2D ambiguity, diversity of human poses, and costs in obtaining multiple views. We propose a novel optimisation scheme that bypasses the prior bias bottleneck and the 2D-pose annotation bottleneck that we identify in single-view reconstruction, and move towards low-resource photo-realistic 3D reconstruction that directly and fully utilises the target image. Our scheme combines domain-specific method SMPLify-X and domain-agnostic inverse rendering method redner, with two simple yet powerful techniques. We demonstrate that our techniques can 1) improve the accuracy of the reconstructed body both qualitatively and quantitatively for challenging inputs, and 2) control optimisation to a selected part only. Our ideas promise extension to more difficult problems and domains even beyond human body reconstruction.
Practical Machine Learning for Rendering: From Research to Deployment
(The Eurographics Association, 2022) Marshall, Carl S.; Vembar, Deepak S.; Ganguly, Sujoy; Guinier, Florent; Hahmann, Stefanie; Patow, Gustavo A.
Applying machine learning to improve graphics rendering or asset pipelines is challenging. Practicalities such as proprietary datasets, network retraining, and deployment issues make it difficult to translate published research into deployed solutions. In this course, industry practitioners at the forefront of this interdisciplinary field discuss and outline potential solutions.
NeuralMLS: Geometry-Aware Control Point Deformation
(The Eurographics Association, 2022) Shechter, Meitar; Hanocka, Rana; Metzer, Gal; Giryes, Raja; Cohen-Or, Daniel; Pelechano, Nuria; Vanderhaeghe, David
We introduce NeuralMLS, a space-based deformation technique, guided by a set of displaced control points. We leverage the power of neural networks to inject the underlying shape geometry into the deformation parameters. The goal of our technique is to enable a realistic and intuitive shape deformation. Our method is built upon moving least-squares (MLS), since it minimizes a weighted sum of the given control point displacements. Traditionally, the influence of each control point on every point in space (i.e., the weighting function) is defined using inverse distance heuristics. In this work, we opt to learn the weighting function, by training a neural network on the control points from a single input shape, and exploit the innate smoothness of neural networks. Our geometry-aware control point deformation is agnostic to the surface representation and quality; it can be applied to point clouds or meshes, including non-manifold and disconnected surface soups. We show that our technique facilitates intuitive piecewise smooth deformations, which are well suited for manufactured objects. We show the advantages of our approach compared to existing surface and space-based deformation techniques, both quantitatively and qualitatively.
Mesh Smoothing for Teaching GLSL Programming
(The Eurographics Association, 2022) Ilinkin, Ivaylo; Bourdin, Jean-Jacques; Paquette, Eric
This paper shares ideas for effective assignment that can be used to introduce a number of advanced GLSL concepts including shader storage buffer objects, transform feedback, and compute shaders. The assignment is based on published research on mesh smoothing which serves as a motivating factor and offers a sense of accomplishment.
Neural Motion Compression with Frequency-adaptive Fourier Feature Network
(The Eurographics Association, 2022) Tojo, Kenji; Chen, Yifei; Umetani, Nobuyuki; Pelechano, Nuria; Vanderhaeghe, David
We present a neural-network-based compression method to alleviate the storage cost of motion capture data. Human motions such as locomotion, often consist of periodic movements. We leverage this periodicity by applying Fourier features to a multilayered perceptron network. Our novel algorithm finds a set of Fourier feature frequencies based on the discrete cosine transformation (DCT) of motion. During training, we incrementally added a dominant frequency of the DCT to a current set of Fourier feature frequencies until a given quality threshold was satisfied. We conducted an experiment using CMU motion dataset, and the results suggest that our method achieves overall high compression ratio while maintaining its quality.
Introduction to Computer Graphics: A Visual Interactive Approach
(The Eurographics Association, 2022) Loscos, Celine; Bourdin, Jean-Jacques; Paquette, Eric
Computer graphics is a difficult topic, requiring associating mathematics and programming skills. When initially taught at undergraduate levels, there are several factors which discourage students. First, programming a first computer graphics program requires a substantial initial framework which can be intimidating for many of them. Second, understanding and applying mathematical concepts is very often overwhelming. To counter this intimidating feeling, a new teaching approach was proposed in 2018 to 3rd year undergraduate computer science students. The course was split into two parts, theory and practice. The theoretical concepts were seen in class, with course handouts and table exercises resembling closely to traditional computer graphics learning. The originality of the course comes from a new way of practicing 3D programming. Practical labs were built upon the Unity game engine programming platform, adapted to match the theoretical concepts seen in classroom. Conclusions are drawn over 4 years of teaching this course. When taught using an accompanying easy-to-access graphics programming platform, computer graphics becomes a more attractive course for students with lower mathematics and programming skills. It is also very satisfactory for skillful students as it enables them to grab and master concepts quickly to reach interesting final lab achievements.

Browse

Browsing EG2022 by Issue Date

Results Per Page

Sort Options