Dense reconstruction on-the-fly

Wendel, Andreas; Maurer, Michael; Graber, Gottfried; Pock, Thomas; Bischof, Horst

doi:10.1109/cvpr.2012.6247833

Cited by 88 publications

(68 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, in [1,4] MVS is applied to photographs of famous landmarks, harvested from online photo-collections. Similarly, the authors of [21] pro-pose using MVS with sequences of images obtained by a remote controlled model helicopter for the purposes of automatic 3D mapping. These examples highlight a detailed understanding of the performance of MVS algorithms under different conditions, which is the purpose of the proposed dataset.…”

Section: Related Workmentioning

confidence: 99%

Large Scale Multi-view Stereopsis Evaluation

Jensen¹,

Dahl²,

Vogiatzis

et al. 2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

444

337

View full text Add to dashboard Cite

The seminal multiple view stereo benchmark evaluations from Middlebury and by Strecha et al. have played a major role in propelling the development of multi-view stereopsis methodology. Although seminal, these benchmark datasets are limited in scope with few reference scenes. Here, we try to take these works a step further by proposing a new multi-view stereo dataset, which is an order of magnitude larger in number of scenes and with a significant increase in diversity. Specifically, we propose a dataset containing 80 scenes of large variability. Each scene consists of 49 or 64 accurate camera positions and reference structured light scans, all acquired by a 6-axis industrial robot. To apply this dataset we propose an extension of the evaluation protocol from the Middlebury evaluation, reflecting the more complex geometry of some of our scenes. The proposed dataset is used to evaluate the state of the art multiview stereo algorithms of Tola et al., Campbell et al. and Furukawa et al. Hereby we demonstrate the usability of the dataset as well as gain insight into the workings and challenges of multi-view stereopsis. Through these experiments we empirically validate some of the central hypotheses of multi-view stereopsis, as well as determining and reaffirming some of the central challenges.

show abstract

Section: Related Workmentioning

confidence: 99%

Large Scale Multi-view Stereopsis Evaluation

Jensen¹,

Dahl²,

Vogiatzis

et al. 2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

444

337

View full text Add to dashboard Cite

show abstract

“…use of TV(z) as a regularizer, although that appears to be common practice in previous works [15,26,25,34,40]. So in the following section, let us clarify how the area form of a perspective depth map parametrization looks like, and highlight its interplay with the TV.…”

Section: Orthographic Minimal-area Regularizermentioning

confidence: 99%

“…1.2 -consider no further. The majority of variational methods resort to implicit handling of depth discontinuities by TV regularization [15,26,25,34,40].…”

Section: Introductionmentioning

confidence: 99%

Efficient minimal-surface regularization of perspective depth maps in variational stereo

Graber

Balzer

Soatto

et al. 2015

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

We propose a method for dense three-dimensional surface reconstruction that leverages the strengths of shapebased approaches, by imposing regularization that respects the geometry of the surface, and the strength of depthmap-based stereo, by avoiding costly computation of surface topology. The result is a near real-time variational reconstruction algorithm free of the staircasing artifacts that affect depth-map and plane-sweeping approaches. This is made possible by exploiting the gauge ambiguity to design a novel representation of the regularizer that is linear in the parameters and hence amenable to be optimized with stateof-the-art primal-dual numerical schemes.

show abstract

“…We describe the uncertainty in the depth map estimate at time k with the entropy H k . In such a way, the treatment is independent on the actual model and the parametric formulation described in Section II might be replaced in order to take into account, for instance, multiple depth hypotheses [30].…”

Section: B the Information Gain Of A Measurementmentioning

confidence: 99%

Appearance-based Active, Monocular, Dense Reconstruction for Micro Aerial Vehicles

Förster

Pizzoli

Scaramuzza

2014

Robotics: Science and Systems X

View full text Add to dashboard Cite

Abstract-In this paper, we investigate the following problem: given the image of a scene, what is the trajectory that a robotmounted camera should follow to allow optimal dense depth estimation? The solution we propose is based on maximizing the information gain over a set of candidate trajectories. In order to estimate the information that we expect from a camera pose, we introduce a novel formulation of the measurement uncertainty that accounts for the scene appearance (i.e., texture in the reference view), the scene depth and the vehicle pose. We successfully demonstrate our approach in the case of realtime, monocular reconstruction from a micro aerial vehicle and validate the effectiveness of our solution in both synthetic and real experiments. To the best of our knowledge, this is the first work on active, monocular dense reconstruction, which chooses motion trajectories that minimize perceptual ambiguities inferred by the texture in the scene.

show abstract

Dense reconstruction on-the-fly

Cited by 88 publications

References 18 publications

Large Scale Multi-view Stereopsis Evaluation

Large Scale Multi-view Stereopsis Evaluation

Efficient minimal-surface regularization of perspective depth maps in variational stereo

Appearance-based Active, Monocular, Dense Reconstruction for Micro Aerial Vehicles

Contact Info

Product

Resources

About