Towards Temporally-Coherent Video Matting

Bai, Xue; Wang, Jue; Simons, David

doi:10.1007/978-3-642-24136-9_6

Cited by 53 publications

(63 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Secondly, if matting is applied as a postprocessing step then it is not clear how to choose the width of the video trimap. Furthermore, frame-by-frame matting may produce temporally inconsistent results, which, to some degree, has been addressed in recent work [30].…”

Section: Results and Comparisonmentioning

confidence: 99%

Alpha-Flow for Video Matting

Sindeev

Konushin

Rother

2013

Computer Vision – ACCV 2012

View full text Add to dashboard Cite

Abstract. This work addresses the problem of video matting, that is extracting the opacity-layer of a foreground object from a video sequence. We introduce the notion of alpha-flow which corresponds to the flow in the opacity layer. The idea is derived from the process of rotoscoping, where a user-supplied object mask is smoothly interpolated between keyframes while preserving its correspondence with the underlying image. Our key contribution is an algorithm which infers both the opacity masks and the alpha-flow in an efficient and unified manner. We embed our algorithm in an interactive video matting system where the first and last frame of a sequence are given as keyframes, and additional user strokes may be provided in intermediate frames. We show high quality results on various challenging sequences, and give a detailed comparison to competing techniques.

show abstract

Section: Results and Comparisonmentioning

confidence: 99%

Alpha-Flow for Video Matting

Sindeev

Konushin

Rother

2013

Computer Vision – ACCV 2012

View full text Add to dashboard Cite

show abstract

“…Many methods [27]- [29] perform binary segmentation using graph cut, after which, morphological operations near the boundary generate a trimap. Optical flow is used in some approaches [26], [30] to propagate the trimap to intermediate frames. Once the trimap is obtained for each frame, image matting algorithms are then applied to extract the matte.…”

Section: Related Workmentioning

confidence: 99%

“…Bai et al [29] use robust matting [11] at each frame, followed by altering the matting Laplacian to bias towards alpha from the previous frame. Filtering the alpha matte temporally using level-set based interpolation is proposed in [30] to ensure temporal coherence. The disadvantage of such post-processing is that it reduces the spatial accuracy of the matte by smoothing the edges.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Sparse Coding for Alpha Matting

Johnson

Varnousfaderani

Cholakkal

et al. 2016

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-Existing color sampling based alpha matting methods use the compositing equation to estimate alpha at a pixel from pairs of foreground (F) and background (B) samples. The quality of the matte depends on the selected (F,B) pairs. In this paper, the matting problem is reinterpreted as a sparse coding of pixel features, wherein the sum of the codes gives the estimate of the alpha matte from a set of unpaired F and B samples. A non-parametric probabilistic segmentation provides a certainty measure on the pixel belonging to foreground or background, based on which a dictionary is formed for use in sparse coding. By removing the restriction to conform to (F,B) pairs, this method allows for better alpha estimation from multiple F and B samples. The same framework is extended to videos, where the requirement of temporal coherence is handled effectively. Here, the dictionary is formed by samples from multiple frames. A multi-frame graph model, as opposed to a single image as for image matting, is proposed that can be solved efficiently in closed form. Quantitative and qualitative evaluations on a benchmark dataset are provided to show that the proposed method outperforms current state-of-the-art in image and video matting.

show abstract

“…All unknown regions have the same width. In case that the foreground object contains both fuzzy and near-solid edges, we allow the user to touch up the unknown region using paint brushes on one image, and use an optical-flow-guided propagation method similar to the one proposed in a previous video matting system [26] to propagate the user modified trimap shape to other images.…”

Section: Pre-processingmentioning

confidence: 99%