LDI tree: A hierarchical representation for image-based rendering

Chun Fa Chang, Gary Bishop, Anselmo Lastra

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

106 Citations (Scopus)

Abstract

Using multiple reference images in 3D image warping has been a challenging problem. Recently, the Layered Depth Image (LDI) was proposed by Shade et al. to merge multiple reference images under a single center of projection, while maintaining the simplicity of warping a single reference image. However it does not consider the issue of sampling rate. We present the LDI tree, which combines a hierarchical space partitioning scheme with the concept of the LDI. It preserves the sampling rates of the reference images by adaptively selecting an LDI in the LDI tree for each pixel. While rendering from the LDI tree, we only have to traverse the LDI tree to the levels that are comparable to the sampling rate of the output image. We also present a progressive refinement feature and a "gap filling" algorithm implemented by pre-filtering the LDI tree. We show that the amount of memory required has the same order of growth as the 2D reference images. This also bounds the complexity of rendering time to be less than directly rendering from all reference images. Copyright ACM 1999.

Original languageEnglish
Title of host publicationProceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999
PublisherAssociation for Computing Machinery, Inc
Pages291-298
Number of pages8
ISBN (Electronic)0201485605, 9780201485608
DOIs
Publication statusPublished - 1999 Jul 1
Event26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999 - Los Angeles, United States
Duration: 1999 Aug 81999 Aug 13

Publication series

NameProceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999

Conference

Conference26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999
CountryUnited States
CityLos Angeles
Period99/8/899/8/13

Fingerprint

Sampling
Pixels
Data storage equipment

Keywords

  • Hierarchical representation
  • Image-based rendering

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design

Cite this

Chang, C. F., Bishop, G., & Lastra, A. (1999). LDI tree: A hierarchical representation for image-based rendering. In Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999 (pp. 291-298). (Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999). Association for Computing Machinery, Inc. https://doi.org/10.1145/311535.311571

LDI tree : A hierarchical representation for image-based rendering. / Chang, Chun Fa; Bishop, Gary; Lastra, Anselmo.

Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999. Association for Computing Machinery, Inc, 1999. p. 291-298 (Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999).

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

Chang, CF, Bishop, G & Lastra, A 1999, LDI tree: A hierarchical representation for image-based rendering. in Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999. Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999, Association for Computing Machinery, Inc, pp. 291-298, 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999, Los Angeles, United States, 99/8/8. https://doi.org/10.1145/311535.311571
Chang CF, Bishop G, Lastra A. LDI tree: A hierarchical representation for image-based rendering. In Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999. Association for Computing Machinery, Inc. 1999. p. 291-298. (Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999). https://doi.org/10.1145/311535.311571
Chang, Chun Fa ; Bishop, Gary ; Lastra, Anselmo. / LDI tree : A hierarchical representation for image-based rendering. Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999. Association for Computing Machinery, Inc, 1999. pp. 291-298 (Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999).
@inproceedings{24ec4898f9f54c6c84595b044ac4f0a0,
title = "LDI tree: A hierarchical representation for image-based rendering",
abstract = "Using multiple reference images in 3D image warping has been a challenging problem. Recently, the Layered Depth Image (LDI) was proposed by Shade et al. to merge multiple reference images under a single center of projection, while maintaining the simplicity of warping a single reference image. However it does not consider the issue of sampling rate. We present the LDI tree, which combines a hierarchical space partitioning scheme with the concept of the LDI. It preserves the sampling rates of the reference images by adaptively selecting an LDI in the LDI tree for each pixel. While rendering from the LDI tree, we only have to traverse the LDI tree to the levels that are comparable to the sampling rate of the output image. We also present a progressive refinement feature and a {"}gap filling{"} algorithm implemented by pre-filtering the LDI tree. We show that the amount of memory required has the same order of growth as the 2D reference images. This also bounds the complexity of rendering time to be less than directly rendering from all reference images. Copyright ACM 1999.",
keywords = "Hierarchical representation, Image-based rendering",
author = "Chang, {Chun Fa} and Gary Bishop and Anselmo Lastra",
year = "1999",
month = "7",
day = "1",
doi = "10.1145/311535.311571",
language = "English",
series = "Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999",
publisher = "Association for Computing Machinery, Inc",
pages = "291--298",
booktitle = "Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999",

}

TY - GEN

T1 - LDI tree

T2 - A hierarchical representation for image-based rendering

AU - Chang, Chun Fa

AU - Bishop, Gary

AU - Lastra, Anselmo

PY - 1999/7/1

Y1 - 1999/7/1

N2 - Using multiple reference images in 3D image warping has been a challenging problem. Recently, the Layered Depth Image (LDI) was proposed by Shade et al. to merge multiple reference images under a single center of projection, while maintaining the simplicity of warping a single reference image. However it does not consider the issue of sampling rate. We present the LDI tree, which combines a hierarchical space partitioning scheme with the concept of the LDI. It preserves the sampling rates of the reference images by adaptively selecting an LDI in the LDI tree for each pixel. While rendering from the LDI tree, we only have to traverse the LDI tree to the levels that are comparable to the sampling rate of the output image. We also present a progressive refinement feature and a "gap filling" algorithm implemented by pre-filtering the LDI tree. We show that the amount of memory required has the same order of growth as the 2D reference images. This also bounds the complexity of rendering time to be less than directly rendering from all reference images. Copyright ACM 1999.

AB - Using multiple reference images in 3D image warping has been a challenging problem. Recently, the Layered Depth Image (LDI) was proposed by Shade et al. to merge multiple reference images under a single center of projection, while maintaining the simplicity of warping a single reference image. However it does not consider the issue of sampling rate. We present the LDI tree, which combines a hierarchical space partitioning scheme with the concept of the LDI. It preserves the sampling rates of the reference images by adaptively selecting an LDI in the LDI tree for each pixel. While rendering from the LDI tree, we only have to traverse the LDI tree to the levels that are comparable to the sampling rate of the output image. We also present a progressive refinement feature and a "gap filling" algorithm implemented by pre-filtering the LDI tree. We show that the amount of memory required has the same order of growth as the 2D reference images. This also bounds the complexity of rendering time to be less than directly rendering from all reference images. Copyright ACM 1999.

KW - Hierarchical representation

KW - Image-based rendering

UR - http://www.scopus.com/inward/record.url?scp=84886838044&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886838044&partnerID=8YFLogxK

U2 - 10.1145/311535.311571

DO - 10.1145/311535.311571

M3 - Conference contribution

AN - SCOPUS:84886838044

T3 - Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999

SP - 291

EP - 298

BT - Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999

PB - Association for Computing Machinery, Inc

ER -