Roxels: responsibility weighted 3D volume reconstruction

Bonet, Jordi; Viola, Paul A.

doi:10.1109/iccv.1999.791251

Cited by 91 publications

(72 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This can lead to large error generation and incorrect 3D reconstruction by creating a hole, even if only one voxel is removed incorrectly. This problem led to the probabilistic approaches to space carving [7,1,6] being desirable. The other advantage of probabilistic approaches is that they avoid the need of a global parameter (variance) for color consistency checks.…”

Section: Introductionmentioning

confidence: 99%

A semisupervised approach to space carving

Prakash

Robles-Kelly

2008

2008 19th International Conference on Pattern Recognition

View full text Add to dashboard Cite

In this paper, we present a semi-supervised approach to space carving by casting the recovery of volumetric data from multiple views into an evidence combining setting. The method presented here is statistical in nature and employs, as a starting point, a manually obtained contour. By making use of this user-provided information, we obtain probabilistic silhouettes of all successive images. These silhouettes provide a prior distribution that is then used to compute the probability of a voxel being carved. This evidence combining setting allows us to make use of background pixel information. As a result, our method combines the advantages of shape-from-silhouette techniques and statistical space carving approaches. For the carving process, we propose a new voxelated space. The proposed space is a projective one that provides a color mapping for the object voxels which is consistent in terms of pixel coverage with their projection onto the image planes for the imagery under consideration. We provide quantitative results and illustrate the utility of the method on real-world imagery.

show abstract

Section: Introductionmentioning

confidence: 99%

A semisupervised approach to space carving

Prakash

Robles-Kelly

2008

2008 19th International Conference on Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Two notable exceptions are the Roxel Algorithm [20] and the Probabilistic Space Carving Algorithm [21], which attempt to capture shape uncertainty by assigning a "soft" occupancy value between zero and one to every voxel in space. Working under the assumption that an accurate treatment of long-range probabilistic dependencies is intractable, these approaches rely on heuristic approximations to assess a voxel's visibility.…”

Section: Introductionmentioning

confidence: 99%

A Probabilistic Theory of Occupancy and Emptiness

Bhotika

Fleet

Kutulakos

2002

Computer Vision — ECCV 2002

View full text Add to dashboard Cite

Abstract. This paper studies the inference of 3D shape from a set of Ò noisy photos. We derive a probabilistic framework to specify what one can infer about 3D shape for arbitrarily-shaped, Lambertian scenes and arbitrary viewpoint configurations. Based on formal definitions of visibility, occupancy, emptiness, and photo-consistency, the theoretical development yields a formulation of the Photo Hull Distribution, the tightest probabilistic bound on the scene's true shape that can be inferred from the photos. We show how to (1) express this distribution in terms of image measurements, (2) represent it compactly by assigning an occupancy probability to each point in space, and (3) design a stochastic reconstruction algorithm that draws fair samples (i.e., 3D photo hulls) from it. We also present experimental results for complex 3D scenes.

show abstract

“…A number of remedies have been proposed for the first shortcoming, e.g., a probabilistic framework [1,4], a level set approach [21], and a method that searches over a pixel neighborhood around a re-projected voxel's position for a color-consistent one [11]. However, these remedies require significant additional computation.…”

mentioning

confidence: 99%