Fast Rendering of Large Crowds Using GPU

Park, Hunki; Han, JungHyun

doi:10.1007/978-3-540-89222-9_24

Cited by 13 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typical applications that can benefit from hardware instancing include rendering of crowds and vegetation, which usually require a large number of instances at the same time as there exists much repetition. In (Park et al, 2009), (Dudash, 2007), and later (Ramos et al, 2012), examples on how to render several thousands of animated characters in real-time with the use of hardware instancing is presented. Recently, (Bao et al, 2012) presented a GPU-driven framework for rendering large forests.…”

Section: Hardware Instancingmentioning

confidence: 99%

See 1 more Smart Citation

Integrating Occlusion Culling and Hardware Instancing for Efficient Real-time Rendering of Building Information Models

Johansson

2013

Proceedings of the International Conference on Computer Graphics Theory and Applications and International Conference on Inform

View full text Add to dashboard Cite

This paper presents an efficient approach for integrating occlusion culling and hardware instancing. The work is primarily targeted at Building Information Models (BIM), which typically share characteristics addressed by these two acceleration techniques separately-high level of occlusion and frequent reuse of building components. Together, these two acceleration techniques complement each other and allows large and complex BIMs to be rendered in real-time. Specifically, the proposed method takes advantage of temporal coherence and uses a lightweight data transfer strategy to provide an efficient hardware instancing implementation. Compared to only using occlusion culling, additional speedups of 1.25x-1.7x is achieved for rendering large BIMs received from real-world projects. These speedups are measured in viewpoints that represents the worst case scenarios in terms of rendering performance when only occlusion culling is utilized.

show abstract

Section: Hardware Instancingmentioning

confidence: 99%

“…Without any type of visibility culling, this may lead to unnecessary high GPU-burden for 3D scenes with many instances. In order to limit the number of instances, (Park et al, 2009) and (Bao et al, 2012) perform view-frustum culling on the GPU.…”

Section: Hardware Instancingmentioning

confidence: 99%

Integrating Occlusion Culling and Hardware Instancing for Efficient Real-time Rendering of Building Information Models

Johansson

2013

Proceedings of the International Conference on Computer Graphics Theory and Applications and International Conference on Inform

View full text Add to dashboard Cite

show abstract

“…Instancing technique is to render multiple instances of the same character with a single drawing call. In OpenGL graphics pipeline, pseudo-instancing has been widely, for example, in [11,12,18], where the crowd rendering is optimized by sharing vertex data, primitive counts and types, among all instances. It minimizes the amount of duplicated data.…”

Section: Performance Evaluationmentioning

confidence: 99%

A Real-Time System for Crowd Rendering: Parallel LOD and Texture-Preserving Approach on GPU

et al. 2011

View full text Add to dashboard Cite

Abstract. In modern games, rendering a massive scene with a large number of animated character is imminent and a very challenging task. In this paper, we present a real-time crowd rendering system on GPUs with a special focus on how to preserve texture appearance in progressive LOD-based mesh simplification algorithms. Our results show that the proposed parallel LOD approach can get up to 5.33 times of speedup compared with the standard pseudo-instancing approach.

show abstract

“…Some advanced methods allow developers to modify the shape proportion of duplications and then retarget rigs and animations to the modified meshes [10,11] or synthesize new motions [12,13]. With the support of hardware-accelerated geometryinstancing and pseudo-instancing techniques [9,[14][15][16], multiple data of a character, including vertices, triangles, textures, skeletons, skinning weights, and animations, can be cached in the memory of a graphics processing unit (GPU). At each time when the virtual scene needs to be rendered, the renderer will alter and assemble those data dynamically without the need of fetching them from CPU main memory.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Large Crowd Rendering with Efficient Character and Instance Management on GPU

Dong

Peng

2019

International Journal of Computer Games Technology

View full text Add to dashboard Cite

Achieving the efficient rendering of a large animated crowd with realistic visual appearance is a challenging task when players interact with a complex game scene. We present a real-time crowd rendering system that efficiently manages multiple types of character data on the GPU and integrates seamlessly with level-of-detail and visibility culling techniques. The character data, including vertices, triangles, vertex normals, texture coordinates, skeletons, and skinning weights, are stored as either buffer objects or textures in accordance with their access requirements at the rendering stage. Our system preserves the view-dependent visual appearance of individual character instances in the crowd and is executed with a fine-grained parallelization scheme. We compare our approach with the existing crowd rendering techniques. The experimental results show that our approach achieves better rendering performance and visual quality. Our approach is able to render a large crowd composed of tens of thousands of animated instances in real time by managing each type of character data in a single buffer object.

show abstract

Fast Rendering of Large Crowds Using GPU

Cited by 13 publications

References 6 publications

Integrating Occlusion Culling and Hardware Instancing for Efficient Real-time Rendering of Building Information Models

Integrating Occlusion Culling and Hardware Instancing for Efficient Real-time Rendering of Building Information Models

A Real-Time System for Crowd Rendering: Parallel LOD and Texture-Preserving Approach on GPU

Real-Time Large Crowd Rendering with Efficient Character and Instance Management on GPU

Contact Info

Product

Resources

About