The City of Sights: Design, construction, and measurement of an Augmented Reality stage set

Gruber, L.; Gauglitz, Steffen; Ventura, Jonathan; Zollmann, Stefanie; Huber, Manuel; Schlegel, Michael; Klinker, Gudrun; Schmalstieg, Dieter; Höllerer, Tobias

doi:10.1109/ismar.2010.5643564

Cited by 23 publications

(13 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This information is highly valuable to drive the reconstruction, that is, to determine what views are most informative for the task at hand. [25]. Dark points are close, bright points are far.…”

Section: Discussionmentioning

confidence: 98%

“…We can see, for instance, that using a threshold σ thr = 6×10 −4 , which is approximately 2 × 10 3 times the initialization value σ max , more than 60% of the depth measurements computed by our method are affected by an error up to 15 centimetres, that is approximately 2.6% of the full depth range. In order to demonstrate the effectiveness of the proposed approach on real time reconstructions, we present our results on the City of Sights stage set [25]. We computed a point cloud from different depth maps acquired by a single hand-held camera.…”

Section: Measurement Uncertaintymentioning

confidence: 99%

See 1 more Smart Citation

REMODE: Probabilistic, monocular dense reconstruction in real time

Pizzoli

Förster

Scaramuzza

2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

298

216

View full text Add to dashboard Cite

In this paper, we solve the problem of estimating dense and accurate depth maps from a single moving camera. A probabilistic depth measurement is carried out in real time on a per-pixel basis and the computed uncertainty is used to reject erroneous estimations and provide live feedback on the reconstruction progress. Our contribution is a novel approach to depth map computation that combines Bayesian estimation and recent development on convex optimization for image processing. We demonstrate that our method outperforms state-of-the-art techniques in terms of accuracy, while exhibiting high efficiency in memory usage and computing power. We call our approach REMODE (REgularized MOnocular Depth Estimation). Our CUDA-based implementation runs at 30Hz on a laptop computer and is released as open-source software. Abstract-In this paper, we solve the problem of estimating dense and accurate depth maps from a single moving camera. A probabilistic depth measurement is carried out in real time on a per-pixel basis and the computed uncertainty is used to reject erroneous estimations and provide live feedback on the reconstruction progress. Our contribution is a novel approach to depth map computation that combines Bayesian estimation and recent development on convex optimization for image processing. We demonstrate that our method outperforms stateof-the-art techniques in terms of accuracy, while exhibiting high efficiency in memory usage and computing power. We call our approach REMODE (REgularized MOnocular Depth Estimation) and the CUDA-based implementation runs at 30Hz on a laptop computer.

show abstract

Section: Discussionmentioning

confidence: 98%

Section: Measurement Uncertaintymentioning

confidence: 99%

REMODE: Probabilistic, monocular dense reconstruction in real time

Pizzoli

Förster

Scaramuzza

2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

298

216

View full text Add to dashboard Cite

show abstract

“…We tested our system on a variety of video sequences, including videos of a panorama dataset by Coffin et al [6] 6 , sequences from the "City of Sights" repository [12] 7 , as well as further selfrecorded videos, using models from the "City of Sights" as backdrop. Results from those videos are presented in Figs.…”

Section: Discussionmentioning

confidence: 99%

“…It should be noted that this is not a flaw of the GRIC score per 6 http://tracking.mat.ucsb.edu 7 http://cityofsights.icg.tugraz.at Figure 9: Our system acting as a SLAM system, reconstructing the scene in 3D and recovering the camera trajectory fully automatically. The input sequence for this model stems from the "City of Sights" repository [12] and was recorded by a robot arm. Each reconstructed 3D feature position is visualized as a small image patch (sampled from the frame in which it was first observed).…”

Section: Discussionmentioning

confidence: 99%

Live tracking and mapping from both general and rotation-only camera motion

Gauglitz

Sweeney

Ventura

et al. 2012

2012 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)

Self Cite

View full text Add to dashboard Cite

We present an approach to real-time tracking and mapping that supports any type of camera motion in 3D environments, that is, general (parallax-inducing) as well as rotation-only (degenerate) motions. Our approach effectively generalizes both a panorama mapping and tracking system and a keyframe-based Simultaneous Localization and Mapping (SLAM) system, behaving like one or the other depending on the camera movement. It seamlessly switches between the two and is thus able to track and map through arbitrary sequences of general and rotation-only camera movements.Key elements of our approach are to design each system component such that it is compatible with both panoramic data and Structure-from-Motion data, and the use of the 'Geometric Robust Information Criterion' to decide whether the transformation between a given pair of frames can best be modeled with an essential matrix E, or with a homography H. Further key features are that no separate initialization step is needed, that the reconstruction is unbiased, and that the system continues to collect and map data after tracking failure, thus creating separate tracks which are later merged if they overlap. The latter is in contrast to most existing tracking and mapping systems, which suspend tracking and mapping, thus discarding valuable data, while trying to relocalize the camera with respect to the initial map.We tested our system on a variety of video sequences, successfully tracking through different camera motions and fully automatically building panoramas as well as 3D structures.

show abstract

“…If the scale of the reconstruction can be determined, for example by aligning the reconstruction to GPS data, we can choose the color map according to predefined resolutions. Figure 1(c) demonstrates this visualization for the reconstructed City-of-Sights [8] paper model.…”

Section: Quality Measuresmentioning

confidence: 96%

Online Feedback for Structure-from-Motion Image Acquisition

Hoppe¹,

Klopschitz²,

Rumpler³

et al. 2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

The quality and completeness of 3D models obtained by Structure-from-Motion (SfM) heavily depend on the image acquisition process. If the user gets feedback about the reconstruction quality already during the acquisition, he can optimize this process. We propose an online SfM approach that allows the inspection of the current reconstruction result on site. To guide the user throughout the acquisition, we visualize the current Ground Sampling Distance (GSD) and image redundancy as quality indicators on the surface model. The contributions of this paper are an online SfM framework for highresolution still images that achieves an accuracy close to an off-line SfM method and a visualization of quality measures that allow the user to optimize the image acquisition process. We compare the accuracy of the proposed online SfM to state-of-the-art batch-based SfM methods and demonstrate how our algorithm improves the acquisition process.

show abstract

The City of Sights: Design, construction, and measurement of an Augmented Reality stage set

Cited by 23 publications

References 41 publications

REMODE: Probabilistic, monocular dense reconstruction in real time

REMODE: Probabilistic, monocular dense reconstruction in real time

Live tracking and mapping from both general and rotation-only camera motion

Online Feedback for Structure-from-Motion Image Acquisition

Contact Info

Product

Resources

About