Barbosa, Joao · CERN Document Server (European Organization for Nuclear Research) · 2019
<!--HTML-->In the age of big data, increasing simulation accuracy, we often need more pixels to show the minute details that traditional single display system cannot provide. Industrial designers such as car manufacturing design teams rely on high-fidelity photorealistic rendering, as supplied by the Intel OSPray framework, to study the interaction of materials and shapes in their designs. The TCP Bridge Display Wall module built on top of Intel OSPRay framework addresses these problems by providing an interactive tool that exploits the power of Intel-based clusters like Stampede2 to achieve interactive high-fidelity model and material rendering with contextual surroundings. In this presentation, we will show the challenges of building and implementing the module, the use cases scenarios, and the current results.
Cited by 0
Tom Van Der Schaaf, Luc Renambot, Desmond Germans et al. · 2002
Introduction The current trend in hardware for parallel graphics is to use clusters of off-the-shelf PCs instead of high-end super computers. This trend has emerged since the dramatic change in the price/performance ratio of today&apos;s PCs. Using large, high-resolution displays is another trend that is currently emerging. High resolution allows for detailed scientific visualization, and overcomes the limited screen resolution of standard monitors. Large displays also have applications in teaching environments, where multiple people (small groups or full classroom) are looking at a single large screen. The goal of this project is to investigate the field of parallel rendering in the context of scalable tiled displays. A renderer calculates a 2D picture from a 3D model specified by the programmer. A parallel renderer uses multiple processors to calculate a single image. The target system for this parallel renderer is a so-called tiled&lt;F13.15
Cited by 0
Jiří Jelínek · 2009
Svět digitalni fotogorafie umožňuje tvorbu obrazů s vysokým rozlisenim, ktere jsou klicove k prohliženi znacně zvětsených obrazů bez ztraty detailu. Obrazy s vysokým rozlisenim musi být stejně jako jakekoli jine upraveny, aby mohly být reprodukovany spravně pro lidske oci. Větsina systemu pro zpracovani obrazů ale neni schopna zpracovat obrazy větsi než je dostupna RAM. Kromě toho jediný monitor dokaže zobrazit pouze malou cast opravdu velkých obrazů. Proto je třeba GUI schopne zobrazovat obrazy na monitorove stěny. Tato prace implementuje podporu pro SAGE, prostředi pro ovladani monitorových stěn, do nip2, GUI pro VIPS, knihovnu vyvinutou pro zpracovani velkých obrazků.
Cited by 0
Marquerie Cordoba, Juan Sebastian · Repositori digital de la UPF (Universitat Pompeu Fabra) · 2023
To Josep Blat, for trusting and giving me the opportunity to be part of this amazing team.To Pablo L. Garcia, for enduring all my grammatical and orthographically errors, that where usually accompanied with my extremely diluted explanations.To the team itself, I am sorry for all the mad ramblings and mishaps that you had to endure this past year, I hope I made it even a tiny bit worth it.To Javier Agenjo, for showing me the never ending quest that is computer graphics, a path that I am going to keep exploring with the best of my abilities, for
Cited by 0Open access
Kai Rohmer, Thorsten Grosch · 2015
Mobile devices are part of our everyday life and allow augmented reality (AR) with their integrated camera image. Recent research has shown that even photorealistic augmentations with consistent illumination are possible. A method, achieving this first, distributed lighting computations and the extraction of the important light sources. To reach real-time frame rates on a mobile device, the number of these extracted light sources must be low, limiting the scope of possible illumination scenarios and the quality of shadows. In this paper, we show how to reduce the computational cost per light using a combination of tile-based rendering and frustum culling techniques tailored for AR applications. Our approach runs entirely on the GPU and does not require any precomputation. Without reducing the displayed image quality, we achieve up to 2.2× speedup for typical AR scenarios.
Cited by 6
Linus Franke, Nikolai Hofmann, Marc Stamminger et al. · Proceedings of the ACM on Computer Graphics and Interactive Techniques · 2018
In this paper we present a scattering-based method to compute high quality depth of field in real time. Relying on multiple layers of scene data, our method naturally supports settings with partial occlusion, an important effect that is often disregarded by real time approaches. Using well-founded layer-reduction techniques and efficient mapping to the GPU, our approach out-performs established approaches with a similar high-quality feature set. Our proposed algorithm works by collecting a multi-layer image, which is then directly reduced to only keep hidden fragments close to discontinuities. Fragments are then further reduced by merging and then splatted to screen-space tiles. The per-tile information is then sorted and accumulated in order, yielding an overall approach that supports partial occlusion as well as properly ordered blending of the out-of-focus fragments.
Cited by 11
Rare & Special e-Zone (The Hong Kong University of Science and Technology) · 2004
Cited by 0
W. Correa, James T. Klosowski, Claudio Silva · Parallel Computing · 2003
Cited by 27
Correa, Wagner T., Klosowski, James T., Silva, Claudio T. · Eurographics · 2002
We present a sort-first parallel system for out-of-core rendering of large models on cluster-based tiled displays. The system is able to render igh-resolution images of large models at interactive frame rates using off-theshelf PCs with small memory. Given a model, we use an out-of-core preprocessing algorithm to build an on-disk hierarchical representation for the model. At run time, each PC renders the image for a display tile, using an out-of-core rendering approach that employs multiple threads to overlap rendering, visibility computation, and disk operations. The system can operate in approximate mode for real-time rendering, or in conservative mode for rendering with guaranteed accuracy. Running our system in approximate mode on a cluster of 16 PCs each with 512 MB of main memory, we are able to render 12-megapixel images of a 13-million-triangle model with 99.3% of accuracy at 10.8 frames per second. Rendering such a large model at high resolutions and interactive frame rates would typically require expensive high-end graphics hardware. Our results show that a cluster of inexpensive PCs is an attractive alternative to those high-end systems.
Cited by 0Open access
Mengjiao Han, Ingo Wald, Will Usher et al. · 2020
We present dw2, a flexible and easy-to-use software infrastructure for interactive rendering of large tiled display walls. Our library represents the tiled display wall as a single virtual screen through a display "service", which renderers connect to and send image tiles to be displayed, either from an on-site or remote cluster. The display service can be easily configured to support a range of typical network and display hardware configurations; the client library provides a straightforward interface for easy integration into existing renderers. We evaluate the performance of our display wall service in different configurations using a CPU and GPU ray tracer, in both on-site and remote rendering scenarios using multiple display walls.
Cited by 6
Xingfu Wu, Valerie Taylor, Jason Leigh et al. · 2008
Cited by 0
Mengjiao Han, Ingo Wald, Will Usher et al. · arXiv (Cornell University) · 2020
We present dw2, a flexible and easy-to-use software infrastructure for interactive rendering of large tiled display walls. Our library represents the tiled display wall as a single virtual screen through a display "service", which renderers connect to and send image tiles to be displayed, either from an on-site or remote cluster. The display service can be easily configured to support a range of typical network and display hardware configurations; the client library provides a straightforward interface for easy integration into existing renderers. We evaluate the performance of our display wall service in different configurations using a CPU and GPU ray tracer, in both on-site and remote rendering scenarios using multiple display walls
Cited by 2Open access
KYUNGJUN, LIM, Researcher, Freederia AI · Figshare · 2025
**Abstract:** This paper introduces a novel algorithmic framework, termed Dynamic Pixel-Level Adaptive Holographic Rendering (DPL-AHR), designed to significantly improve viewing angle performance and reduce perceived distortions in large-format tiled holographic displays. Existing systems often suffer from spatial discontinuities and parallax errors at tile junctions due to the inherent limitations in holographic projection and alignment. DPL-AHR addresses this issue by dynamically adjusting pixel rendering parameters on a per-pixel basis, accounting for the viewer’s position and the geometrical inaccuracies of the tiled array. This approach leverages real-time eye-tracking data, advanced ray-tracing algorithms, and machine learning-driven optimization to achieve a near-seamless holographic experience across a wider range of viewing angles, paving the way for advanced immersive applications in entertainment, medical visualization, and design. --- *This document is a part of the Freederia Research Archive. Explore our complete collection of advanced research at [en.freederia.com](https://en.freederia.com), or visit our main portal at [freederia.com](https://freederia.com) to learn more about our mission and other initiatives.*
Cited by 0Open access
KYUNGJUN, LIM, Researcher, Freederia AI · Figshare · 2025
**Abstract:** This paper introduces a novel algorithmic framework, termed Dynamic Pixel-Level Adaptive Holographic Rendering (DPL-AHR), designed to significantly improve viewing angle performance and reduce perceived distortions in large-format tiled holographic displays. Existing systems often suffer from spatial discontinuities and parallax errors at tile junctions due to the inherent limitations in holographic projection and alignment. DPL-AHR addresses this issue by dynamically adjusting pixel rendering parameters on a per-pixel basis, accounting for the viewer’s position and the geometrical inaccuracies of the tiled array. This approach leverages real-time eye-tracking data, advanced ray-tracing algorithms, and machine learning-driven optimization to achieve a near-seamless holographic experience across a wider range of viewing angles, paving the way for advanced immersive applications in entertainment, medical visualization, and design. --- *This document is a part of the Freederia Research Archive. Explore our complete collection of advanced research at [en.freederia.com](https://en.freederia.com), or visit our main portal at [freederia.com](https://freederia.com) to learn more about our mission and other initiatives.*
Cited by 0Open access
R Frank · University of North Texas Digital Library (University of North Texas) · 2001
This case study highlights the technical challenges of creating an application that uses a multithreaded scene graph toolkit for rendering and uses a software environment for management of tiled display systems. Scene graph toolkits simplify and streamline graphics applications by providing data management and rendering services. Software for tiled display environments typically performs device and event management by opening windows on displays, by gathering and processing input device events, and by orchestrating the execution of application rendering code. These environments serve double-duty as frameworks for creating parallel rendering applications. We explore technical issues related to interfacing scene graph systems with software that manages tiled projection systems in the context of an implementation, and formulate suggestions for the future growth of such systems.
Cited by 1Open access
Eibner, Gottfried · reposiTUm (TU Wien) · 2003
High-end rendering systems have provided the computer graphics community over a long period with high resolution graphics at high frame rates, allowing to build up large tiled displays.But with the increasing performance of commodity computer and graphics hardware we are able to build such large displays without the costs of high-end rendering systems.The key concept is to build an inexpensive large tiled display for interactive 3D graphics, composed of multiple overlapping projections, driven by a PC based rendering cluster.In this thesis we will show how to build up a tiled display from scratch using oblique projectors to display high-resolution scenery.Each projector is driven by a PC.The PCs are connected to form a network that is capable to share and distribute data and scenery content.All projected images together form a large high-resolution tiled display.To run the tiled display and compensate distortion coming from oblique projection, we have implemented a software to calibrate the projectors and find their relative poses.The software package undistorts oblique projectors used for the tiled display and generates blending masks for overlapping projection areas.Both undistortion and blending masks are used to run a seamless tiled display.While undistortion guarantees the continuity of geometry displayed by different projectors, blending masks make overlapping regions appear seamless and equally bright.Without blending masks overlapping regions would appear brighter than the other regions.This would lead to regions of different brightness.
Cited by 0Open access
2015
Rendering efficiently a massive amount of local light sources had already been solved by methods such as tiled deferred shading [Andersson 09], tiled forward shading [Billeter et al. 13], and clustered deferred and forward shading [Olsson et al. 12]. However, generating appropriate shadows for a large number of light sources in real time is still an ongoing topic. Since accurate shadows from direct lights significantly improve the final image and give the viewer additional information about the scene arrangement, their generation is an important part of real-time rendering.
Cited by 0
Jourdain, Sebastien, Li, Forrest, Martin, Ken et al. · Zenodo (CERN European Organization for Nuclear Research) · 2022
23.4.0 (2022-03-25) Bug Fixes <strong>actor2d:</strong> rendering of 2D actors in tiled viewports (f2106a7) Features add vtkSphereWidget (f261709) <strong>ITKHelper:</strong> Add conversion functions for PolyData (b2c3443)
Cited by 0Open access
Nirnimesh Narayanan Nirnimesh · 2008
Tiled displays can provide high resolution and large display area. Cluster-based tiled displays are cost-effective and scalable. Chromium is a popular software API used to build such displays; Chromium based tiled displays tend to be network-limited affecting the scalability in the number of nodes and the ability to handle really large environment models. We present a tiled Display Wall setup based on a client-server architecture. Our system uses offthe -shelf graphics hardware and standard ethernet network. High-level scene structure and hierarchy of a scene graph is used by a central server to minimize network load. Visible parts of the scene graph are transmitted and cached by the clients to take advantage of temporal coherence. The server exploits the high degree of overlap in the computation space for each rendering node to avoid concurrent redundant computations. We use a broadcast oriented protocol to the clients making the system scalable. Geometry push philosophy from the server helps keep the clients in sync with one another and facilitates the pipelining of the constituent stages. Distributed rendering allows the display wall to render scenes which are otherwise too bulky for any of the individual rendering nodes. No node, including the server, needs to render the entire environment, making our system suitable for interactive rendering of massive models. We show performance measures for the different underlying aspects of our display wall consisting of up to 44 tiles. Studies show that the server and network loads grow sublinearly with the number of tiles. This makes our scheme suitable for the construction of very large-resolution displays. 1.
Cited by 0
Zhang, Xingang, Guo, Shanchuan, Du, Peijun et al. · Figshare · 2024
The HQTP30 is available for free download. It represents a high-accuracy terrain model of the QTP within the WGS84 coordinate system (EPSG: 4326) and is referenced to the EGM2008 Geoid. This dataset encompasses the entire QTP area with a spatial resolution of 1 arc-second (≈30 m) and is divided into a total of 494 tiled files. Each of these tiled file measures 1° by 1° and is stored in Geotiff format. The naming convention for these files follows a structured format: HQTP30_Naa_Ebbb.tif, where “aa” corresponds to the latitude, and “bbb” corresponds to the longitude. For example, HQTP30_N30_E090 represents a tiled file covering the region from N30° to 31° and E90° to 91°. To enhance user accessibility and facilitate a quick assessment of the dataset’s quality and characteristics, 3D rendering previews are provided for each tiled file.
Cited by 1Open access