Tales of Shape and Radiance in Multi-view Stereo

Authors:
Stefano Soatto;Anthony J. Yezzi;Hailin Jin
Affiliations:
-;-;-
Venue:
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Year:
2003

Citing 0
Cited 14

Silhouette and stereo fusion for 3D object modeling

Computer Vision and Image Understanding - Model-based and image-based 3D scene representation for interactive visalization
Multi-View Stereo Reconstruction of Dense Shape and Complex Appearance

International Journal of Computer Vision
Multi-View Stereo Reconstruction and Scene Flow Estimation with a Global Image-Based Matching Score

International Journal of Computer Vision
Mumford-Shah on the Move: Region-Based Segmentation on Deforming Manifolds with Application to 3-D Reconstruction of Shape and Appearance from Multi-View Images

Journal of Mathematical Imaging and Vision
Carved Visual Hulls for Image-Based Modeling

International Journal of Computer Vision
Continuous Global Optimization in Multiview 3D Reconstruction

International Journal of Computer Vision
Generic Scene Recovery Using Multiple Images

SSVM '09 Proceedings of the Second International Conference on Scale Space and Variational Methods in Computer Vision
Joint Estimation of Shape and Reflectance using Multiple Images with Known Illumination Conditions

International Journal of Computer Vision
Using the orthographic projection model to approximate the perspective projection model for 3D facial reconstruction

PSIVT'07 Proceedings of the 2nd Pacific Rim conference on Advances in image and video technology
An iterative surface evolution algorithm for multiview stereo

Journal on Image and Video Processing - Special issue on fast and robust methods for multiple-view vision
Gradient Flows for Optimizing Triangular Mesh-based Surfaces: Applications to 3D Reconstruction Problems Dealing with Visibility

International Journal of Computer Vision
Video-based descriptors for object recognition

Image and Vision Computing
Carved visual hulls for image-based modeling

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Sparse Occlusion Detection with Optical Flow

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

To what extent can three-dimensional shape and radiancebe inferred from a collection of images? Can the two be estimatedseparately while retaining optimality? How shouldthe optimality criterion be computed? When is it necessaryto employ an explicit model of the reflectance properties ofa scene? In this paper we introduce a separation principlefor shape and radiance estimation that applies to Lambertianscenes and holds for any choice of norm. When thescene is not Lambertian, however, shape cannot be decoupledfrom radiance, and therefore matching image-to-imageis not possible directly. We employ a rank constraint onthe radiance tensor, which is commonly used in computergraphics, and construct a novel cost functional whose minimizationleads to an estimate of both shape and radiancefor non-Lambertian objects, which we validate experimentally.