A post-textured architecture for effective occlusion culling

Moon Hee Choi, Shin-Dug Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a new rasterization pipeline based on the tiling traversal algorithm, which can reduce considerably the unnecessary processing cycles occurring in pixel processing step. This architecture can perform efficient occlusion culling at an early stage of the rasterization pipeline by retrieving data from the depth-table. In addition, the proposed architecture can reduce memory bandwidth waste caused by fetching texture data that are obscured by performing z-test before texture mapping. Specifically this scheme might cause a consistency problem for the frame memory if more than two fragments have the same pixel address. However, by using a flagging scheme for the pixel cache, it can detect the overlap condition and maintain the consistency. Simulation results show that the proposed architecture can achieve around 34% performance gain, compared with the conventional pre-textured architecture, and around 11%, compared with the conventional post-textured architecture. Proceedings of the 2005 International Conference on Computer Vision, VlSlON'05.

Original languageEnglish
Title of host publicationProceedings of the 2005 International Conference on Computer Vision, VISION'05
Pages262-267
Number of pages6
Publication statusPublished - 2005 Dec 1
Event2005 International Conference on Computer Vision, VISION'05 - Las Vegas, NV, United States
Duration: 2005 Jun 202005 Jun 23

Other

Other2005 International Conference on Computer Vision, VISION'05
CountryUnited States
CityLas Vegas, NV
Period05/6/2005/6/23

Fingerprint

Pixels
Pipelines
Textures
Data storage equipment
Processing
Computer vision
Bandwidth
Rasterization

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Choi, M. H., & Kim, S-D. (2005). A post-textured architecture for effective occlusion culling. In Proceedings of the 2005 International Conference on Computer Vision, VISION'05 (pp. 262-267)
Choi, Moon Hee ; Kim, Shin-Dug. / A post-textured architecture for effective occlusion culling. Proceedings of the 2005 International Conference on Computer Vision, VISION'05. 2005. pp. 262-267
@inproceedings{b1af15af38924c32989ad7c2912ed512,
title = "A post-textured architecture for effective occlusion culling",
abstract = "We present a new rasterization pipeline based on the tiling traversal algorithm, which can reduce considerably the unnecessary processing cycles occurring in pixel processing step. This architecture can perform efficient occlusion culling at an early stage of the rasterization pipeline by retrieving data from the depth-table. In addition, the proposed architecture can reduce memory bandwidth waste caused by fetching texture data that are obscured by performing z-test before texture mapping. Specifically this scheme might cause a consistency problem for the frame memory if more than two fragments have the same pixel address. However, by using a flagging scheme for the pixel cache, it can detect the overlap condition and maintain the consistency. Simulation results show that the proposed architecture can achieve around 34{\%} performance gain, compared with the conventional pre-textured architecture, and around 11{\%}, compared with the conventional post-textured architecture. Proceedings of the 2005 International Conference on Computer Vision, VlSlON'05.",
author = "Choi, {Moon Hee} and Shin-Dug Kim",
year = "2005",
month = "12",
day = "1",
language = "English",
isbn = "9781932415650",
pages = "262--267",
booktitle = "Proceedings of the 2005 International Conference on Computer Vision, VISION'05",

}

Choi, MH & Kim, S-D 2005, A post-textured architecture for effective occlusion culling. in Proceedings of the 2005 International Conference on Computer Vision, VISION'05. pp. 262-267, 2005 International Conference on Computer Vision, VISION'05, Las Vegas, NV, United States, 05/6/20.

A post-textured architecture for effective occlusion culling. / Choi, Moon Hee; Kim, Shin-Dug.

Proceedings of the 2005 International Conference on Computer Vision, VISION'05. 2005. p. 262-267.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A post-textured architecture for effective occlusion culling

AU - Choi, Moon Hee

AU - Kim, Shin-Dug

PY - 2005/12/1

Y1 - 2005/12/1

N2 - We present a new rasterization pipeline based on the tiling traversal algorithm, which can reduce considerably the unnecessary processing cycles occurring in pixel processing step. This architecture can perform efficient occlusion culling at an early stage of the rasterization pipeline by retrieving data from the depth-table. In addition, the proposed architecture can reduce memory bandwidth waste caused by fetching texture data that are obscured by performing z-test before texture mapping. Specifically this scheme might cause a consistency problem for the frame memory if more than two fragments have the same pixel address. However, by using a flagging scheme for the pixel cache, it can detect the overlap condition and maintain the consistency. Simulation results show that the proposed architecture can achieve around 34% performance gain, compared with the conventional pre-textured architecture, and around 11%, compared with the conventional post-textured architecture. Proceedings of the 2005 International Conference on Computer Vision, VlSlON'05.

AB - We present a new rasterization pipeline based on the tiling traversal algorithm, which can reduce considerably the unnecessary processing cycles occurring in pixel processing step. This architecture can perform efficient occlusion culling at an early stage of the rasterization pipeline by retrieving data from the depth-table. In addition, the proposed architecture can reduce memory bandwidth waste caused by fetching texture data that are obscured by performing z-test before texture mapping. Specifically this scheme might cause a consistency problem for the frame memory if more than two fragments have the same pixel address. However, by using a flagging scheme for the pixel cache, it can detect the overlap condition and maintain the consistency. Simulation results show that the proposed architecture can achieve around 34% performance gain, compared with the conventional pre-textured architecture, and around 11%, compared with the conventional post-textured architecture. Proceedings of the 2005 International Conference on Computer Vision, VlSlON'05.

UR - http://www.scopus.com/inward/record.url?scp=60749091556&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=60749091556&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:60749091556

SN - 9781932415650

SP - 262

EP - 267

BT - Proceedings of the 2005 International Conference on Computer Vision, VISION'05

ER -

Choi MH, Kim S-D. A post-textured architecture for effective occlusion culling. In Proceedings of the 2005 International Conference on Computer Vision, VISION'05. 2005. p. 262-267