A Survey of Methods for Volumetric Scene Reconstruction from Photographs

Slabaugh, Greg; Schafer, Ronald W.; Malzbender, Tom; Culbertson, Bruce

doi:10.1007/978-3-7091-6756-4_6

Cited by 103 publications

(74 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This carving process is either a plane sweep one [7] or an operation on the surface voxels being considered [36]. This carving process can be single sweep or iterative in nature and is governed by the intersection of the rays from the surface voxels to the images in the sequence.…”

Section: Space Carvingmentioning

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: Space Carvingmentioning

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

“…A volumetric grid where each element (voxel) is tested against S is a simple and robust way to generate an approximate surface, but requires an additional quantisation step [17]. The volumetric visual hull can be refined by removing voxels which fail a colour consistency test [10] , although regions of a uniform or regular appearance can lead to unreliable refinement of the surface.…”

Section: Background Theorymentioning

confidence: 99%

Projective surface refinement for free-viewpoint video

Miller

Starck

Hilton

2006

3rd European Conference on Visual Media Production (CVMP 2006). Part of the 2nd Multimedia Conference 2006

View full text Add to dashboard Cite

This paper introduces a novel method of surface refinement for free-viewpoint video of dynamic scenes. Unlike previous approaches, the method presented here uses both visual hull and silhouette contours to constrain refinement of viewdependent depth maps from wide baseline views. A technique for extracting silhouette contours as rims in 3D from the view-dependent visual hull (VDVH) is presented. A new method for improving correspondence is introduced, where refinement of the VDVH is posed as a global problem in projective ray space. Artefacts of global optimisations are reduced by incorporating rims as constraints. Real time rendering of virtual views in a free-viewpoint video system is achieved using an image+depth representation for each real view. Results illustrate the high quality of rendered views achieved through this refinement technique.

show abstract

“…In the context of robot vision, most papers deal with 3D reconstruction and focus on modeling accuracy. Classically, this is done either considering geometric objects (in that case, techniques are based on primitive reconstruction [6,12]) or representing the shapes thanks to meshes [3] or using an exhausting voxel representation of the scene (see [16] for a recent survey of methods involving sample representations), eventually reducing the complexity by means of hierarchical techniques like octrees. But, for several kinds of applications such as path planning, obstacle avoidance or exploration, only a preliminary 3D map of the scene is sufficient.…”

Section: Overviewmentioning

confidence: 99%