Integration of Multiview Stereo and Silhouettes Via Convex Functionals on Convex Domains

Kolev, Kalin; Cremers, Daniel

doi:10.1007/978-3-540-88682-2_57

Cited by 42 publications

(45 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We start by referring to the MVS evaluation by [23]. Looking at the top performers in that evaluation, we can distinguish two main trends: region growing methods [8,11,12,20] and occlusion-robust photo-consistency methods [3,5,10,13,18,27]. The best performing region growing method [8] uses a combination of photo-consistency based patch fitting, growing and filtering in order to reconstruct the scene of interest.…”

Section: Previous Workmentioning

confidence: 99%

Video-based, real-time multi-view stereo

Vogiatzis

Hernández

2011

Image and Vision Computing

139

125

View full text Add to dashboard Cite

We investigate the problem of obtaining a dense reconstruction in real-time, from a live video stream. In recent years, Multi-view stereo (MVS) has received considerable attention and a number of methods have been proposed. However, most methods operate under the assumption of a relatively sparse set of still images as input and unlimited computation time. Video based MVS has received less attention despite the fact that video sequences offer significant benefits in terms of usability of MVS systems. In this paper we propose a novel video based MVS algorithm that is suitable for real-time, interactive 3d modeling with a hand-held camera. The key idea is a per-pixel, probabilistic depth estimation scheme that updates posterior depth distributions with every new frame. The current implementation is capable of updating 15 million distributions per second. We evaluate the proposed method against the state-of-the-art real-time MVS method and show improvement in terms of accuracy. AbstractWe investigate the problem of obtaining a dense reconstruction in real-time, from a live video stream. In recent years, Multi-view stereo (MVS) has received considerable attention and a number of methods have been proposed. However, most methods operate under the assumption of a relatively sparse set of still images as input and unlimited computation time. Video based MVS has received less attention despite the fact that video sequences offer significant benefits in terms of usability of MVS systems. In this paper we propose a novel video based MVS algorithm that is suitable for real-time, interactive 3d modeling with a hand-held camera. The key idea is a per-pixel, probabilistic depth estimation scheme that updates posterior depth distributions with every new frame. The current implementation is capable of updating 15 million distributions per second. We evaluate the proposed method against the state-of-the-art real-time MVS method and show improvement in terms of accuracy.

show abstract

Section: Previous Workmentioning

confidence: 99%

Video-based, real-time multi-view stereo

Vogiatzis

Hernández

2011

Image and Vision Computing

139

125

View full text Add to dashboard Cite

show abstract

“…However, a more thorough matching technique using a local planarity assumption such as [17] would also greatly improve results in challenging scenes. The framework we describe in this chapter has been widely adopted by a variety of multi-view stereo algorithms [7,8,18,20,24,29,38,42,47]. This can be mainly justified by the simplicity of the approach, but also by the flexibility that it offers, e.g.…”

Section: Discussionmentioning

confidence: 99%

“…These algorithms include deformable surfaces [20], Poisson reconstruction [17], signed distance functions [18], Delaunay [7] or MRFs [22,29,47].…”

Section: Computing Photo-consistency From a Set Of Calibrated Photogrmentioning

confidence: 99%

See 1 more Smart Citation

Shape from Photographs: A Multi-view Stereo Pipeline

Hernández

Vogiatzis

2010

Studies in Computational Intelligence

View full text Add to dashboard Cite

Acquiring 3d shape from images is a classic problem in Computer Vision occupying researchers for at least 20 years. Only recently however have these ideas matured enough to provide highly accurate results. We present a complete algorithm to reconstruct 3d objects from images using the stereo correspondence cue. The technique can be described as a pipeline of four basic building blocks: camera calibration, image segmentation, photo-consistency estimation from images, and surface extraction from photo-consistency. In this chapter we will put more emphasis on the latter two: namely how to extract geometric information from a set of photographs without explicit camera visibility, and how to combine different geometry estimates in an optimal way.

show abstract

“…In a convex formulation of multiple view 3D reconstruction, it was recently shown [15] that one can impose additional convex constraints which assure that the computed minimal surfaces are silhouette-consistent. Essentially this constraint can be seen as a volume constraint: The volume along any ray from the camera center must be at least 1 if that ray passes through the silhouette and zero otherwise.…”

Section: Shape Priors For Image Segmentationmentioning

confidence: 99%

Moment Constraints in Convex Optimization for Segmentation and Tracking

Klodt¹,

Steinbrücker²,

Cremers³

2013

Advanced Topics in Computer Vision

Self Cite

View full text Add to dashboard Cite

Convex relaxation techniques have become a popular approach to shape optimization as they allow to compute solutions independent of initialization to a variety of problems. In this chapter, we will show that shape priors in terms of moment constraints can be imposed within the convex optimization framework, since they give rise to convex constraints. In particular, the lower-order moments correspond to the overall area, the centroid, and the variance or covariance of the shape and can be easily imposed in interactive segmentation methods. Respective constraints can be imposed as hard constraints or soft constraints. Quantitative segmentation studies on a variety of images demonstrate that the user can impose such constraints with a few mouse clicks, leading to substantial improvements of the resulting segmentation, and reducing the average segmentation error from 12% to 0.35%. GPU-based computation times of around 1 second allow for interactive segmentation.

show abstract

Integration of Multiview Stereo and Silhouettes Via Convex Functionals on Convex Domains

Cited by 42 publications

References 23 publications

Video-based, real-time multi-view stereo

Video-based, real-time multi-view stereo

Shape from Photographs: A Multi-view Stereo Pipeline

Moment Constraints in Convex Optimization for Segmentation and Tracking

Contact Info

Product

Resources

About