Markerless Motion Capture with unsynchronized moving cameras

Hasler, Nils; Rosenhahn, Bodo; Thormählen, Thorsten; Wand, Michael; Gall, Jüergen; Seidel, Hans‐Peter

doi:10.1109/cvprw.2009.5206859

Cited by 71 publications

(77 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For a geometric proxy scenario, we use the data set by Hasler et al [12], which includes two HD cameras at wide baselines. We manually construct a coarse geometry, then start with world coordinates and perform the same procedure beginning at Eq.…”

Section: Stage 1: Approximate Depthmentioning

confidence: 99%

Integrating approximate depth data into dense image correspondence estimation

Ruhl

Klose

Lipski

et al. 2012

Proceedings of the 9th European Conference on Visual Media Production - CVMP '12

View full text Add to dashboard Cite

High-quality dense image correspondence estimation between two images is an essential prerequisite for many tasks in visual media production, one prominent example being view interpolation. Due to the ill-posed nature of the correspondence estimation problem, errors occur frequently for a number of problematic conditions, among them occlusions, large displacements and low-textured regions. In this paper, we propose to use approximate depth data from low-resolution depth sensors or coarse geometric proxies to guide the high-resolution image correspondence estimation. We counteract the effect of uncertainty in the prior by exploiting the coarse-tofine image pyramid used in our estimation algorithm. Our results show that even with only approximate priors, visual quality improves considerably compared to an unguided algorithm or a pure depth-based interpolation.

show abstract

Section: Stage 1: Approximate Depthmentioning

confidence: 99%

Integrating approximate depth data into dense image correspondence estimation

Ruhl

Klose

Lipski

et al. 2012

Proceedings of the 9th European Conference on Visual Media Production - CVMP '12

View full text Add to dashboard Cite

show abstract

“…As another example, in motion capturing, an actor is typically recorded from different angles resulting in several video streams showing the same scene from different perspectives. Here, the corresponding audio tracks can be used to synchronize the various videos streams, which facilitates a multi-version analysis of the given scene [6].…”

Section: E E E P R O O F W E B V E R S I O Nmentioning

confidence: 99%

Towards Cross-Version Harmonic Analysis of Music

Ewert

Müller

Konz

et al. 2012

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Abstract-For a given piece of music, there often exist multiple versions belonging to the symbolic (e.g., MIDI representations), acoustic (audio recordings), or visual (sheet music) domain. Each type of information allows for applying specialized, domain-specific approaches to music analysis tasks. In this paper, we formulate the idea of a cross-version analysis for comparing and/or combining analysis results from different representations. As an example, we realize this idea in the context of harmonic analysis to automatically evaluate MIDI-based chord labeling procedures using annotations given for corresponding audio recordings. To this end, one needs reliable synchronization procedures that automatically establish the musical relationship between the multiple versions of a given piece. This becomes a hard problem when there are significant local deviations in these versions. We introduce a novel late-fusion approach that combines different alignment procedures in order to identify reliable parts in synchronization results. Then, the cross-version comparison of the various chord labeling results is performed only on the basis of the reliable parts. Finally, we show how inconsistencies in these results across the different versions allow for a quantitative and qualitative evaluation, which not only indicates limitations of the employed chord labeling strategies but also deepens the understanding of the underlying music material.

show abstract

“…by [60]. In a preprocessing step the sub-frame time offsets between the cameras are determined automatically [61,62]. Our scene model represents the scene geometry as a set of small tangent plane patches.…”

Section: Overviewmentioning

confidence: 99%

Towards Plenoptic Raumzeit Reconstruction

Eisemann

Klose

Magnor

2011

Video Processing and Computational Video

View full text Add to dashboard Cite

Abstract. The goal of image-based rendering is to evoke a visceral sense of presense in a scene using only photographs or videos. A huge variety of different approaches have been developed during the last decade. Examining the underlying models we find three different main categories: view interpolation based on geometry proxies, pure image interpolation techniques and complete scene flow reconstruction. In this paper we present three approaches for free-viewpoint video, one for each of these categories and discuss their individual benefits and drawbacks. We hope that studying the different approaches will help others in making important design decisions when planning a free-viewpoint video system.

show abstract

Markerless Motion Capture with unsynchronized moving cameras

Cited by 71 publications

References 24 publications

Integrating approximate depth data into dense image correspondence estimation

Integrating approximate depth data into dense image correspondence estimation

Towards Cross-Version Harmonic Analysis of Music

Towards Plenoptic Raumzeit Reconstruction

Contact Info

Product

Resources

About