Practical, real-time studio matting using dual imagers

@inproceedings{McGuire2006PracticalRS,
  title={Practical, real-time studio matting using dual imagers},
  author={Morgan McGuire and Wojciech Matusik and William S. Yerazunis},
  booktitle={EGSR '06},
  year={2006}
}
This paper presents a practical system for capturing high-resolution video mattes using cameras that contain two imagers on one optical axis. The dual imagers capture registered frames that differ only by defocus or polarization at pixels corresponding to special background 'gray-screens.' This system eliminates color spill and other drawbacks of blue-screen matting while preserving many of its desirable properties (e.g., unassisted, real-time, natural illumination) over more recent methods… 
Real-time Video Matting for Mixed Reality using Depth Generated Trimaps
TLDR
This work combines a low fidelity depth image that segments the original video signal with a real-time parallel natural image matting technique that favors objects with similar colors in the foreground and background to provide real- time alpha mattes for Mixed Reality scenarios that take place in relatively controlled environments.
Extracting depth and matte using a color-filtered aperture
TLDR
A color alignment measure is developed to estimate disparities between the RGB planes for depth reconstruction, and color misalignment cues in the matting algorithm are exploited in order to disambiguate between the foreground and background regions even where their colors are similar.
Extracting depth and matte using a color-filtered aperture
TLDR
A color alignment measure is developed to estimate disparities between the RGB planes for depth reconstruction, and color misalignment cues in the matting algorithm are exploited in order to disambiguate between the foreground and background regions even where their colors are similar.
Towards Real-time Mixed Reality Matting In Natural Scenes
TLDR
This research addresses ways to automatically solve an alpha matte for an image in realtime, and by extension a video, using a consumer level GPU, and is particularly interested in automatically generating trimaps from depth buffers for dynamic scenes so that algorithms requiring more dense constraints may be used.
Real-time automatic chroma-key matting using perceptual analysis and prediction
  • Ling Yin, Jiying Zhao
  • Computer Science
    2014 IEEE 27th Canadian Conference on Electrical and Computer Engineering (CCECE)
  • 2014
TLDR
The qualitative evaluation shows that the determined alpha mattes and foreground colors especially in large seemingly translucent areas are more acceptable by human eyes, and the quantitative comparison between the mechanism and other existing approaches also validates the advantage in speed and quality.
Automatic Real-Time Video Matting Using Time-of-Flight Camera and Multichannel Poisson Equations
TLDR
An automatic real-time video matting system that combines color and depth cues in a probabilistic fusion framework to automatically generate trimaps for live videos, advocating a Time-of-Flight camera-based approach to video bilayer segmentation.
Computer Vision for Visual Effects
TLDR
Computer Vision for Visual Effects will educate students, engineers, and researchers about the fundamental computer vision principles and state-of-the-art algorithms used to create cutting-edge visual effects for movies and television.
Error-concealed image-based rendering
TLDR
This thesis focuses on different techniques to diminish visible artifacts when combining multiple images in a common image domain, and produces novel images, or novel video sequences rendered in real-time, when dealing with video footage from multiple cameras.
Real-time video matting using multichannel poisson equations
TLDR
Quantitative evaluation on still images shows that the alpha mattes extracted using the presented algorithm is much more accurate than the ones obtained using the global Poisson matting algorithm and are comparable to that of other state-of-the-art offline image matting techniques.
Near-Real-Time Image Matting with Known Background
TLDR
A novel matting algorithm for handling cases where foreground objects are in front of complex (non-smooth) but known background that takes the gradient of the known background into consideration is presented.
...
1
2
...

References

SHOWING 1-10 OF 49 REFERENCES
Environment matting extensions: towards higher accuracy and real-time capture
TLDR
This work extends environment matting in two opposite directions: recovering a more accurate model at the expense of using additional structured light backdrops, and obtaining a simplified matte using just a single backdrop.
Defocus video matting
TLDR
This work proposes a novel, fully autonomous method for pulling a matte using multiple synchronized video streams that share a point of view but differ in their plane of focus, and solves the fully dynamic video matting problem without user assistance.
Environment matting and compositing
This paper introduces a new process, environment matting, which captures not just a foreground object and its traditional opacity matte from a real-world scene, but also a description of how that
Performance relighting and reflectance transformation with time-multiplexed illumination
TLDR
The approach is to illuminate the subject with a sequence of time-multiplexed basis lighting conditions, and to record these conditions with a high-speed video camera so that many conditions are recorded in the span of the desired output frame interval.
Performance relighting and reflectance transformation with time-multiplexed illumination
TLDR
The approach is to illuminate the subject with a sequence of time-multiplexed basis lighting conditions, and to record these conditions with a high-speed video camera so that many conditions are recorded in the span of the desired output frame interval.
Blue screen matting
TLDR
The mathematics of constant color matting is presented and proven to be unsolvable as generally practiced, and constraints on the general problem that lead to solutions are demonstrated, or at least significantly prune the search space of solutions.
Light Field Photography with a Hand-held Plenoptic Camera
This paper presents a camera that samples the 4D light field on its sensor in a single photographic exposure. This is achieved by inserting a microlens array between the sensor and main lens,
Segmentation with invisible keying signal
  • M. Ben-Ezra
  • Computer Science
    Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662)
  • 2000
TLDR
A new method for automatic keying using invisible signal is presented, which can be used in real-time and no user assistance is required and has unlimited color range for foreground objects.
High-quality video view interpolation using a layered representation
TLDR
This paper shows how high-quality video-based rendering of dynamic scenes can be accomplished using multiple synchronized video streams combined with novel image-based modeling and rendering algorithms, and develops a novel temporal two-layer compressed representation that handles matting.
Video matting of complex scenes
TLDR
A Bayesian matting technique uses the flowed trimaps to yield high-quality mattes of moving foreground elements with complex boundaries filmed by a moving camera, and a novel technique for smoke matte extraction is also demonstrated.
...
1
2
3
4
5
...