Image-Based Rendering of Range Data with Estimated Depth Uncertainty

Authors:
Christian Hofsetz;Kim Ng;George Chen;Peter McGuinness;Nelson Max;Yang Liu
Affiliations:
Universidade do Vale do Rio dos Sinos;STMicroelectronics San Diego Laboratory;STMicroelectronics San Diego Laboratory;STMicroelectronics San Diego Laboratory;University of California, Davis;University of California, Davis
Venue:
IEEE Computer Graphics and Applications
Year:
2004

Citing 9
Cited 2

Light field rendering

SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
The lumigraph

SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
Hierarchical rendering of trees from precomputed multi-layer z-buffers

Proceedings of the eurographics workshop on Rendering techniques '96
Interactive volume rendering

VVS '89 Proceedings of the 1989 Chapel Hill workshop on Volume visualization
Surfels: surface elements as rendering primitives

Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Unstructured lumigraph rendering

Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Generalized Multiple Baseline Stereo and Direct Virtual View Synthesis Using Range-Space Search, Match, and Render

International Journal of Computer Vision
EWA volume splatting

Proceedings of the conference on Visualization '01
A Multiple-Baseline Stereo

IEEE Transactions on Pattern Analysis and Machine Intelligence

Point-sampled 3D video of real-world scenes

Image Communication
Ambient point clouds for view interpolation

ACM SIGGRAPH 2010 papers

Quantified Score

Hi-index	0.00

Visualization

Abstract

It's difficult to get accurate depth information with computer vision's 3D estimation techniques. When the estimated depths are uncertain, conventional image-based rendering algorithms fails and the view rendering quality suffers. This article demonstrates an image-based rendering algorithm that can render good quality views even when the estimated depths are uncertain. Instead of only using the depth information per pixel, this approach computes a depth uncertainty region. We show how to extract the depth from the input images and how to compute the uncertainty region. The article shows how to render depth with uncertainty by splatting 3D ellipsoidal Gaussian kernels.