When Is the Shape of a Scene Unique Given Its Light-Field: A Fundamental Theorem of 3D Vision?

Authors:
Simon Baker;Terence Sim;Takeo Kanade
Affiliations:
-;-;-
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2003

Citing 12
Cited 4

A Bayesian approach to binocular stereopsis

International Journal of Computer Vision
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
Robot Vision

Robot Vision
A Theory of Shape by Space Carving

International Journal of Computer Vision - Special issue on Genomic Signal Processing
A Multiple-Baseline Stereo

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Visual Hull Concept for Silhouette-Based Image Understanding

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Layered Approach to Stereo Reconstruction

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Stereo in the presence of specular reflection

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Vision in Bad Weather

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Visual hull construction, alignment and refinement for human kinematic modeling, motion tracking and rendering

Visual hull construction, alignment and refinement for human kinematic modeling, motion tracking and rendering
Variational principles, surface evolution, PDEs, level set methods, and the stereo problem

IEEE Transactions on Image Processing

Appearance-Based Face Recognition and Light-Fields

IEEE Transactions on Pattern Analysis and Machine Intelligence
Towards space: time light field rendering

Proceedings of the 2005 symposium on Interactive 3D graphics and games
Real-time view synthesis from a sparse set of views

Image Communication
Space-Time Light Field Rendering

IEEE Transactions on Visualization and Computer Graphics

Quantified Score

Hi-index	0.14

Visualization

Abstract

The complete set of measurements that could ever be used by a passive 3D vision algorithm is the plenoptic function or light-field. We give a concise characterization of when the light-field of a Lambertian scene uniquely determines its shape and, conversely, when the shape is inherently ambiguous. In particular, we show that stereo computed from the light-field is ambiguous if and only if the scene is radiating light of a constant intensity (and color, etc.) over an extended region.