Temporal trimap propagation for video matting using inferential statistics

Sarim, Muhammad; Hilton, Adrian; Guillemaut, Jean-Yves

doi:10.1109/icip.2011.6115797

Cited by 6 publications

(10 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We apply these independently to each view and frame, generating scribbles for each ground truthed frame. The tri-map propagation (TriProp) approach of Sarim et al was also compared against, and was initialised manually at t = 0 as per [5] using only a single tri-map key as input.…”

Section: Resultsmentioning

confidence: 99%

“…[26] Tri.Prop. [5] an Eigenmodel built from the mean (µ) and covariance (C) of RGB colour samples of the background (obtained manually in the first frame). Each pixel's colour c is thresholded via (c−µ)C −1 (c−µ) T < T RGBeigen .…”

Section: Resultsmentioning

confidence: 99%

“…The MRF is solved once per frame to extract the binary mattes for all views simultaneously. Our solution of all views in a single step contrasts with existing methods that either propagate labels between pairs of independently solved views [5], or build foreground appearance models across all views but then independently solve the segmentation for each view [6]. Additionally, we contribute a propagation strategy in which soft labelling constraints are carried forward in time to influence the MRFs defined over subsequent frames, so enhancing the coherence of the resulting matte sequence.…”

Section: Introductionmentioning

confidence: 98%

“…Graph-cut [17] and convex optimization [18] have also been explored for simultaneous estimation. Weaker geometric information is incorporated by Sarim et al who propagate trimaps between views by matching along the epipolar line [5]. Recently Djelouah et al [6] proposed a geometry-free approach, building foreground and background appearance models simultaneously across views using expectation maximisation.…”

Section: A Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Wide Baseline Multi-view Video Matting Using a Hybrid Markov Random Field

Wang

Collomosse

Hilton

2014

2014 22nd International Conference on Pattern Recognition

Self Cite

View full text Add to dashboard Cite

Abstract-We describe a novel framework for segmenting a time-and view-coherent foreground matte sequence from synchronised multiple view video. We construct a Markov Random Field (MRF) comprising links between superpixels corresponded across views, and links between superpixels and their constituent pixels. Texture, colour and disparity cues are incorporated to model foreground appearance. We solve using a multi-resolution iterative approach enabling an eight view high definition (HD) frame to be processed in less than a minute. Furthermore we incorporate a temporal diffusion process introducing a prior on the MRF using information propagated from previous frames, and a facility for optional user correction. The result is a set of temporally coherent mattes solved for simultaneously across views for each frame, exploiting similarities across views and time.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 98%

Section: A Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Wide Baseline Multi-view Video Matting Using a Hybrid Markov Random Field

Wang

Collomosse

Hilton

2014

2014 22nd International Conference on Pattern Recognition

Self Cite

View full text Add to dashboard Cite

show abstract

“…Segmentation from multiple wide-baseline views has been proposed by exploiting appearance similarity [6,19,38]. These approaches assume static backgrounds and different colour distributions for the foreground and back-ground [27,6] which limits applicability for general scenes. In contrast to overcome these limitations, the proposed approaches initialised the foreground object segmentation from wide-baseline feature correspondence followed by joint segmentation and reconstruction.…”

Section: Joint Segmentation and Reconstructionmentioning

confidence: 99%

General Dynamic Scene Reconstruction from Multiple View Video

Mustafa

Kim

Guillemaut

et al. 2015

2015 IEEE International Conference on Computer Vision (ICCV)

Self Cite

View full text Add to dashboard Cite

This paper introduces a general approach to dynamic scene reconstruction from multiple moving cameras without prior knowledge or limiting constraints on the scene structure, appearance, or illumination. Existing techniques for dynamic scene reconstruction from multiple wide-baseline camera views primarily focus on accurate reconstruction in controlled environments, where the cameras are fixed and calibrated and background is known. These approaches are not robust for general dynamic scenes captured with sparse moving cameras. Previous approaches for outdoor dynamic scene reconstruction assume prior knowledge of the static background appearance and structure. The primary contributions of this paper are twofold: an automatic method for initial coarse dynamic scene segmentation and reconstruction without prior knowledge of background appearance or structure; and a general robust approach for joint segmentation refinement and dense reconstruction of dynamic scenes from multiple wide-baseline static or moving cameras. Evaluation is performed on a variety of indoor and outdoor scenes with cluttered backgrounds and multiple dynamic non-rigid objects such as people. Comparison with state-of-the-art approaches demonstrates improved accuracy in both multiple view segmentation and dense reconstruction. The proposed approach also eliminates the requirement for prior knowledge of scene structure and appearance.

show abstract

Video cloning for paintings via artistic style transfer

Liu

2020

SIViP

View full text Add to dashboard Cite

Temporal trimap propagation for video matting using inferential statistics

Cited by 6 publications

References 12 publications

Wide Baseline Multi-view Video Matting Using a Hybrid Markov Random Field

Wide Baseline Multi-view Video Matting Using a Hybrid Markov Random Field

General Dynamic Scene Reconstruction from Multiple View Video

Video cloning for paintings via artistic style transfer

Contact Info

Product

Resources

About