VDR-AM: View-Dependent Representation of Articulated Models

by Pio Claudio, Dohyeong Kim, Tae-Joon Kim and Sung-Eui Yoon
Journal of WSCG, Vol.21, No. 3

Video(10MB)

This figure shows two images of an exhibition crowd scene that has 1 K articulated characters. All the characters and the scene have 83 M triangles. Our method achieves 46 frames per second (fps) on average for this model with 0.5 pixel-of-error (PoE) in a 1280 by 720 HD screen resolution.

Abstract

We present a novel, View-Dependent Representation of Articulated Models (VDR-AM), and show its main benefits in the context of view-dependent rendering integrated with occlusion culling for large-scale crowd scenes. In order to provide varying resolutions on each animated, articulated model, we propose to use a cluster hierarchy in the VDR-AM for an articulated model. The cluster hierarchy serves as a dual representation for both view-dependent rendering and occlusion culling. For a high-performance view-dependent rendering and occlusion culling, we construct each cluster of the cluster hierarchy to contain a spatially coherent portion of the mesh that also has similar simplification errors. To achieve our goal, we present an error-aware clustering method for articulated models. We also identify a subset of animation poses that well represents the original pose data and perform the well-known quadrics-based simplification to efficiently compute our representation, while achieving a high quality simplification. At runtime, we choose a LOD cut from the cluster hierarchy given a user specified error bound in the screen space and render all the visible clusters in the LOD cut. We implement our method in GPU and achieve interactive performance (e.g., 40 frames per second) for large-scale crowd scenes that consist up to thousands of articulated models and 242 M triangles, without noticeable visual artifacts.

Contents

Paper: VDR-AM: View-Dependent Representation of Articulated Models,
@ARTICLE{Claudio2013,
 author = {Claudio, Pio and Kim, DoHyeong and Kim,Tae-Joon and Yoon,Sung-eui},
 editor = {Skala, V.},
 title = {VDR-AM: View-Dependent Representation of Articulated Models},
 journal = {Journal of WSCG},
 volume = {21},
 number = {3},
 year = {2013},
 publisher = {UNION Agency-Science Press},
 issn = {1213-6972},
 conference = {WSCG'2013 - 21st International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision'2013}
}
@inproceedings{Kim:2010:IVR:1900354.1900414,
 author = {Kim, Dohyeong and Claudio, Pio and Kim, Tae-Joon and Yoon, Sung Eui},
 title = {Interactive View-dependent Rendering with Culling for Articulated Models in Crowd Scenes},
 booktitle = {ACM SIGGRAPH ASIA 2010 Posters},
 series = {SA '10},
 year = {2010},
 isbn = {978-1-4503-0524-2},
 location = {Seoul, Republic of Korea},
 pages = {54:1--54:1},
 articleno = {54},
 numpages = {1},
 url = {http://doi.acm.org/10.1145/1900354.1900414},
 doi = {10.1145/1900354.1900414},
 acmid = {1900414},
 publisher = {ACM},
 address = {New York, NY, USA},
} 

Benchmark Data

Models used can be downloaded here

Related Links

Quick-VDR: Interactive View-Dependent Rendering of Massive Models

SGLab

Dept. of Computer Science
KAIST
373-1 Guseong-dong, Yuseong-gu, Daejeon, 305-701
South Korea
sglabkaist dot gmail dot com