Topic
Graphics
About: Graphics is a research topic. Over the lifetime, 17394 publications have been published within this topic receiving 411468 citations. The topic is also known as: graphic.
Papers published on a yearly basis
Papers
More filters
••
IBM1
TL;DR: The concept of multimedia objects as components of an object-based model for a multimedia system is introduced and the essential new synchronization requirement is restricted blocking together with synchronization features covering real-time aspects.
Abstract: Multimedia is defined as the integrated generation, representation, processing, storage, and dissemination of independent machine-processable information expressed in multiple time-dependent and time-independent media such as data, graphics, drawings, voice, audio, and video. The characteristics of synchronization mechanisms desirable for central and distributed multimedia systems are addressed. The concept of multimedia objects as components of an object-based model for a multimedia system is introduced. The essential new synchronization requirement is restricted blocking together with synchronization features covering real-time aspects. Existing synchronization mechanisms can be altered or new ones defined to meet these requirements. >
413 citations
•
[...]
PARC1
TL;DR: The Graphics GEMS series as discussed by the authors provides tips, techniques, and algorithms for graphics programmers with a common desire to share interesting ideas and tools with their colleagues, and each volume provides a new set of innovative solutions to a variety of programming problems.
Abstract: From the Publisher:
"The GRAPHICS GEMS Series" was started in 1990 by Andrew Glassner. The vision and purpose of the Series was - and still is - to provide tips, techniques, and algorithms for graphics programmers. All of the gems are written by programmers who work in the field and are motivated by a common desire to share interesting ideas and tools with their colleagues. Each volume provides a new set of innovative solutions to a variety of programming problems
410 citations
••
08 Sep 2018TL;DR: In this article, spectral convolutions on a mesh surface are used to learn a non-linear representation of a face using mesh sampling operations that enable a hierarchical mesh representation that captures nonlinear variations in shape and expression at multiple scales within the model.
Abstract: Learned 3D representations of human faces are useful for computer vision problems such as 3D face tracking and reconstruction from images, as well as graphics applications such as character generation and animation Traditional models learn a latent representation of a face using linear subspaces or higher-order tensor generalizations Due to this linearity, they can not capture extreme deformations and non-linear expressions To address this, we introduce a versatile model that learns a non-linear representation of a face using spectral convolutions on a mesh surface We introduce mesh sampling operations that enable a hierarchical mesh representation that captures non-linear variations in shape and expression at multiple scales within the model In a variational setting, our model samples diverse realistic 3D faces from a multivariate Gaussian distribution Our training data consists of 20,466 meshes of extreme expressions captured over 12 different subjects Despite limited training data, our trained model outperforms state-of-the-art face models with 50% lower reconstruction error, while using 75% fewer parameters We show that, replacing the expression space of an existing state-of-the-art face model with our model, achieves a lower reconstruction error Our data, model and code are available at http://comaistuempgde/
396 citations
••
03 Aug 1997TL;DR: An optimization algorithm for constructing PSC representations for graphics surface models, and the framework on models that are both geometrically and topologically complex is demonstrated.
Abstract: In this paper, we introduce the progressive simplicial complex (PSC) representation, a new format for storing and transmitting triangulated geometric models. Like the earlier progressive mesh (PM) representation, it captures a given model as a coarse base model together with a sequence of refinement transformations that progressively recover detail. The PSC representation makes use of a more general refinement transformation, allowing the given model to be an arbitrary triangulation (e.g. any dimension, non-orientable, non-manifold, non-regular), and the base model to always consist of a single vertex. Indeed, the sequence of refinement transformations encodes both the geometry and the topology of the model in a unified multiresolution framework. The PSC representation retains the advantages of PM’s. It defines a continuous sequence of approximating models for runtime level-of-detail control, allows smooth transitions between any pair of models in the sequence, supports progressive transmission, and offers a space-efficient representation. Moreover, by allowing changes to topology, the PSC sequence of approximations achieves better fidelity than the corresponding PM sequence. We develop an optimization algorithm for constructing PSC representations for graphics surface models, and demonstrate the framework on models that are both geometrically and topologically complex. CR Categories: I.3.5 [Computer Graphics]: Computational Geometry and Object Modeling surfaces and object representations. Additional
394 citations
••
391 citations