A Video Database for the Development of Stereo-3D Post-Production Algorithms

Corrigan, Desmond; Pitié, François; Morris, Valerie B.; Rankin, Andrew; Linnane, Mark; Kearney, Gavin; Gorzel, Marcin; O'Dea, M.; Lee, C.; Kokaram, Anil

doi:10.1109/cvmp.2010.16

Cited by 12 publications

(10 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the information can be recovered on the other view and along time, before the fall of the raindrop. The original video is available in the database presented in Corrigan et al 7 An example of large object removal is presented in Fig. 6.…”

Section: Results and Future Workmentioning

confidence: 99%

“…7 This can hamper binocular merging, so we use Pitié and Kokaram's Colour Mapping 14 process (implemented as a standalone plug-in for NUKE 15 ) to equalise the colour range across views before any processing (see the first two columns of Fig. 1).…”

Section: Preprocessingmentioning

confidence: 99%

“…[2][3][4][5][6] However there has been little consideration of the problem in stereo, and as the production of stereoscopic content is rapidly increasing, so is the need for new tools to manipulate that content. Apart from object removal, applications of stereo inpainting include view synthesis, image-based modeling, occlusion generation for stereoscopic displays, 6 replacement of saturated areas in one of the two views of a stereo video 7 (due to differences in camera set-up), etc.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Stereo video inpainting

Raimbault

Kokaram

2011

SPIE Proceedings

View full text Add to dashboard Cite

As the production of stereoscopic content increases, so does the need for post-production tools for that content. Video inpainting has become an important tool for rig removal but there has been little consideration of the problem in stereo. This paper presents an algorithm for stereo video inpainting that builds on existing exemplarbased video completion and also considers the issues of view consistency. Given user selected regions in the sequence which may be in the same location in several frames and in both views, the objective is to fill in this area using all the available picture information. Existing algorithms lack temporal consistency, causing flickering and other artefacts. This paper explores the use of long-term picture information across many frames in order to achieve temporal consistency at the same time as exploiting inter-view dependencies within the same framework.

show abstract

Section: Results and Future Workmentioning

confidence: 99%

Section: Preprocessingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Stereo video inpainting

Raimbault

Kokaram

2011

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…Now we have explained how our technique works we analyse userassisted segmentation results on a few sequences extracted from a stereo-video database available online [6]. We keep 100 frames for every sequence in our tests.…”

Section: Experiments and Resultsmentioning

confidence: 99%

User-assisted sparse stereo-video segmentation

Raimbault

Pitié

Kokaram

2013

Proceedings of the 10th European Conference on Visual Media Production

View full text Add to dashboard Cite

Motion-based video segmentation has been studied for many years and remains challenging. Ill-posed problems must be solved when seeking for a fully automated solution, so it is increasingly popular to maintain users in the processing loop by letting them set parameters or draw mattes to guide the segmentation process. When processing multiple-view videos, however, the amount of user interaction should not be proportional to the number of views. In this paper we present a novel sparse segmentation algorithm for twoview stereoscopic videos that maintains temporal coherence and view consistency throughout. We track feature points on both views with a generic tracker and analyse the pairwise affinity of both temporally overlapping and disjoint tracks, whereas existing similar techniques only exploit the information available when tracks overlap. The use of stereo-disparity also allows our technique to process jointly feature tracks on both views, exhibiting a good view consistency in the segmentation output. To make up for the lack of high level understanding inherent to segmentation techniques, we allow the user to refine the output with a split-and-merge approach so as to obtain a desired view-consistent segmentation output over many frames in a few clicks. We present several real video examples to illustrate the versatility of our technique.

show abstract

“…However, not all of the sequences are freely available, and only a few have Full-HD resolution. A database of stereoscopic videos captured with Full-HD cameras mounted on a rig and covering various scenarios and contents is presented in [4] with the aim of facilitating the research on post-production techniques. Finally, it is also worth noting the popular dataset presented in [5] with material used as a benchmark for the performance evaluation of depth estimation algorithms.…”

Section: Introductionmentioning

confidence: 99%

NAMA3DS1-COSPAD1: Subjective video quality assessment database on coding conditions introducing freely available high quality 3D stereoscopic sequences

Urvoy

Barkowsky

Cousseau

et al. 2012

2012 Fourth International Workshop on Quality of Multimedia Experience

117

View full text Add to dashboard Cite

Research in stereoscopic 3D coding, transmission and subjective assessment methodology depends largely on the availability of source content that can be used in cross-lab evaluations. While several studies have already been presented using proprietary content, comparisons between the studies are difficult since discrepant contents are used. Therefore in this paper, a freely available dataset of high quality Full-HD stereoscopic sequences shot with a semiprofessional 3D camera is introduced in detail. The content was designed to be suited for usage in a wide variety of applications, including high quality studies. A set of depth maps was calculated from the stereoscopic pair. As an application example, a subjective assessment has been performed using coding and spatial degradations. The Absolute Category Rating with Hidden Reference method was used. The observers were instructed to vote on video quality only. Results of this experiment are also freely available and will be presented in this paper as a first step towards objective video quality measurement for 3DTV.

show abstract

A Video Database for the Development of Stereo-3D Post-Production Algorithms

Cited by 12 publications

References 17 publications

Stereo video inpainting

Stereo video inpainting

User-assisted sparse stereo-video segmentation

NAMA3DS1-COSPAD1: Subjective video quality assessment database on coding conditions introducing freely available high quality 3D stereoscopic sequences

Contact Info

Product

Resources

About