Citation and metadata
Recommended citation
Christian Lipski, Christian Linz, Thomas Neumann, Markus Wacker, and Marcus Magnor, High Resolution Image Correspondences for Video Post-Production. JVRB - Journal of Virtual Reality and Broadcasting, 9(2012), no. 8. (urn:nbn:de:0009-6-35543)
Download Citation
Endnote
%0 Journal Article %T High Resolution Image Correspondences for Video Post-Production %A Lipski, Christian %A Linz, Christian %A Neumann, Thomas %A Wacker, Markus %A Magnor, Marcus %J JVRB - Journal of Virtual Reality and Broadcasting %D 2012 %V 9(2012) %N 8 %@ 1860-2037 %F lipski2012 %X We present an algorithm for estimating dense image correspondences. Our versatile approach lends itself to various tasks typical for video post-processing, including image morphing, optical flow estimation, stereo rectification, disparity/depth reconstruction, and baseline adjustment. We incorporate recent advances in feature matching, energy minimization, stereo vision, and data clustering into our approach. At the core of our correspondence estimation we use Efficient Belief Propagation for energy minimization.While state-of-the-art algorithms only work on thumbnail-sized images, our novel feature downsampling scheme in combination with a simple, yet efficient data term compression, can cope with high-resolution data. The incorporation of SIFT (Scale-Invariant Feature Transform) features into data term computation further resolves matching ambiguities, making long-range correspondence estimation possible. We detect occluded areas by evaluating the correspondence symmetry, we further apply Geodesic matting to automatically determine plausible values in these regions. %L 004 %K Belief Propagation %K Dense Image Correspondences %K Depth Reconstruction %K Optical Flow %K Video Post-Production %R 10.20385/1860-2037/9.2012.8 %U http://nbn-resolving.de/urn:nbn:de:0009-6-35543 %U http://dx.doi.org/10.20385/1860-2037/9.2012.8Download
Bibtex
@Article{lipski2012, author = "Lipski, Christian and Linz, Christian and Neumann, Thomas and Wacker, Markus and Magnor, Marcus", title = "High Resolution Image Correspondences for Video Post-Production", journal = "JVRB - Journal of Virtual Reality and Broadcasting", year = "2012", volume = "9(2012)", number = "8", keywords = "Belief Propagation; Dense Image Correspondences; Depth Reconstruction; Optical Flow; Video Post-Production", abstract = "We present an algorithm for estimating dense image correspondences. Our versatile approach lends itself to various tasks typical for video post-processing, including image morphing, optical flow estimation, stereo rectification, disparity/depth reconstruction, and baseline adjustment. We incorporate recent advances in feature matching, energy minimization, stereo vision, and data clustering into our approach. At the core of our correspondence estimation we use Efficient Belief Propagation for energy minimization.While state-of-the-art algorithms only work on thumbnail-sized images, our novel feature downsampling scheme in combination with a simple, yet efficient data term compression, can cope with high-resolution data. The incorporation of SIFT (Scale-Invariant Feature Transform) features into data term computation further resolves matching ambiguities, making long-range correspondence estimation possible. We detect occluded areas by evaluating the correspondence symmetry, we further apply Geodesic matting to automatically determine plausible values in these regions.", issn = "1860-2037", doi = "10.20385/1860-2037/9.2012.8", url = "http://nbn-resolving.de/urn:nbn:de:0009-6-35543" }Download
RIS
TY - JOUR AU - Lipski, Christian AU - Linz, Christian AU - Neumann, Thomas AU - Wacker, Markus AU - Magnor, Marcus PY - 2012 DA - 2012// TI - High Resolution Image Correspondences for Video Post-Production JO - JVRB - Journal of Virtual Reality and Broadcasting VL - 9(2012) IS - 8 KW - Belief Propagation KW - Dense Image Correspondences KW - Depth Reconstruction KW - Optical Flow KW - Video Post-Production AB - We present an algorithm for estimating dense image correspondences. Our versatile approach lends itself to various tasks typical for video post-processing, including image morphing, optical flow estimation, stereo rectification, disparity/depth reconstruction, and baseline adjustment. We incorporate recent advances in feature matching, energy minimization, stereo vision, and data clustering into our approach. At the core of our correspondence estimation we use Efficient Belief Propagation for energy minimization.While state-of-the-art algorithms only work on thumbnail-sized images, our novel feature downsampling scheme in combination with a simple, yet efficient data term compression, can cope with high-resolution data. The incorporation of SIFT (Scale-Invariant Feature Transform) features into data term computation further resolves matching ambiguities, making long-range correspondence estimation possible. We detect occluded areas by evaluating the correspondence symmetry, we further apply Geodesic matting to automatically determine plausible values in these regions. SN - 1860-2037 UR - http://nbn-resolving.de/urn:nbn:de:0009-6-35543 DO - 10.20385/1860-2037/9.2012.8 ID - lipski2012 ER -Download
Wordbib
<?xml version="1.0" encoding="UTF-8"?> <b:Sources SelectedStyle="" xmlns:b="http://schemas.openxmlformats.org/officeDocument/2006/bibliography" xmlns="http://schemas.openxmlformats.org/officeDocument/2006/bibliography" > <b:Source> <b:Tag>lipski2012</b:Tag> <b:SourceType>ArticleInAPeriodical</b:SourceType> <b:Year>2012</b:Year> <b:PeriodicalTitle>JVRB - Journal of Virtual Reality and Broadcasting</b:PeriodicalTitle> <b:Volume>9(2012)</b:Volume> <b:Issue>8</b:Issue> <b:Url>http://nbn-resolving.de/urn:nbn:de:0009-6-35543</b:Url> <b:Url>http://dx.doi.org/10.20385/1860-2037/9.2012.8</b:Url> <b:Author> <b:Author><b:NameList> <b:Person><b:Last>Lipski</b:Last><b:First>Christian</b:First></b:Person> <b:Person><b:Last>Linz</b:Last><b:First>Christian</b:First></b:Person> <b:Person><b:Last>Neumann</b:Last><b:First>Thomas</b:First></b:Person> <b:Person><b:Last>Wacker</b:Last><b:First>Markus</b:First></b:Person> <b:Person><b:Last>Magnor</b:Last><b:First>Marcus</b:First></b:Person> </b:NameList></b:Author> </b:Author> <b:Title>High Resolution Image Correspondences for Video Post-Production</b:Title> <b:Comments>We present an algorithm for estimating dense image correspondences. Our versatile approach lends itself to various tasks typical for video post-processing, including image morphing, optical flow estimation, stereo rectification, disparity/depth reconstruction, and baseline adjustment. We incorporate recent advances in feature matching, energy minimization, stereo vision, and data clustering into our approach. At the core of our correspondence estimation we use Efficient Belief Propagation for energy minimization.While state-of-the-art algorithms only work on thumbnail-sized images, our novel feature downsampling scheme in combination with a simple, yet efficient data term compression, can cope with high-resolution data. The incorporation of SIFT (Scale-Invariant Feature Transform) features into data term computation further resolves matching ambiguities, making long-range correspondence estimation possible. We detect occluded areas by evaluating the correspondence symmetry, we further apply Geodesic matting to automatically determine plausible values in these regions.</b:Comments> </b:Source> </b:Sources>Download
ISI
PT Journal AU Lipski, C Linz, C Neumann, T Wacker, M Magnor, M TI High Resolution Image Correspondences for Video Post-Production SO JVRB - Journal of Virtual Reality and Broadcasting PY 2012 VL 9(2012) IS 8 DI 10.20385/1860-2037/9.2012.8 DE Belief Propagation; Dense Image Correspondences; Depth Reconstruction; Optical Flow; Video Post-Production AB We present an algorithm for estimating dense image correspondences. Our versatile approach lends itself to various tasks typical for video post-processing, including image morphing, optical flow estimation, stereo rectification, disparity/depth reconstruction, and baseline adjustment. We incorporate recent advances in feature matching, energy minimization, stereo vision, and data clustering into our approach. At the core of our correspondence estimation we use Efficient Belief Propagation for energy minimization.While state-of-the-art algorithms only work on thumbnail-sized images, our novel feature downsampling scheme in combination with a simple, yet efficient data term compression, can cope with high-resolution data. The incorporation of SIFT (Scale-Invariant Feature Transform) features into data term computation further resolves matching ambiguities, making long-range correspondence estimation possible. We detect occluded areas by evaluating the correspondence symmetry, we further apply Geodesic matting to automatically determine plausible values in these regions. ERDownload
Mods
<mods> <titleInfo> <title>High Resolution Image Correspondences for Video Post-Production</title> </titleInfo> <name type="personal"> <namePart type="family">Lipski</namePart> <namePart type="given">Christian</namePart> </name> <name type="personal"> <namePart type="family">Linz</namePart> <namePart type="given">Christian</namePart> </name> <name type="personal"> <namePart type="family">Neumann</namePart> <namePart type="given">Thomas</namePart> </name> <name type="personal"> <namePart type="family">Wacker</namePart> <namePart type="given">Markus</namePart> </name> <name type="personal"> <namePart type="family">Magnor</namePart> <namePart type="given">Marcus</namePart> </name> <abstract>We present an algorithm for estimating dense image correspondences. Our versatile approach lends itself to various tasks typical for video post-processing, including image morphing, optical flow estimation, stereo rectification, disparity/depth reconstruction, and baseline adjustment. We incorporate recent advances in feature matching, energy minimization, stereo vision, and data clustering into our approach. At the core of our correspondence estimation we use Efficient Belief Propagation for energy minimization. While state-of-the-art algorithms only work on thumbnail-sized images, our novel feature downsampling scheme in combination with a simple, yet efficient data term compression, can cope with high-resolution data. The incorporation of SIFT (Scale-Invariant Feature Transform) features into data term computation further resolves matching ambiguities, making long-range correspondence estimation possible. We detect occluded areas by evaluating the correspondence symmetry, we further apply Geodesic matting to automatically determine plausible values in these regions.</abstract> <subject> <topic>Belief Propagation</topic> <topic>Dense Image Correspondences</topic> <topic>Depth Reconstruction</topic> <topic>Optical Flow</topic> <topic>Video Post-Production</topic> </subject> <classification authority="ddc">004</classification> <relatedItem type="host"> <genre authority="marcgt">periodical</genre> <genre>academic journal</genre> <titleInfo> <title>JVRB - Journal of Virtual Reality and Broadcasting</title> </titleInfo> <part> <detail type="volume"> <number>9(2012)</number> </detail> <detail type="issue"> <number>8</number> </detail> <date>2012</date> </part> </relatedItem> <identifier type="issn">1860-2037</identifier> <identifier type="urn">urn:nbn:de:0009-6-35543</identifier> <identifier type="doi">10.20385/1860-2037/9.2012.8</identifier> <identifier type="uri">http://nbn-resolving.de/urn:nbn:de:0009-6-35543</identifier> <identifier type="citekey">lipski2012</identifier> </mods>Download
Full Metadata
Bibliographic Citation | JVRB, 9(2012), no. 8. |
---|---|
Title |
High Resolution Image Correspondences for Video Post-Production (eng) |
Author | Christian Lipski, Christian Linz, Thomas Neumann, Markus Wacker, Marcus Magnor |
Language | eng |
Abstract | We present an algorithm for estimating dense image correspondences. Our versatile approach lends itself to various tasks typical for video post-processing, including image morphing, optical flow estimation, stereo rectification, disparity/depth reconstruction, and baseline adjustment. We incorporate recent advances in feature matching, energy minimization, stereo vision, and data clustering into our approach. At the core of our correspondence estimation we use Efficient Belief Propagation for energy minimization. While state-of-the-art algorithms only work on thumbnail-sized images, our novel feature downsampling scheme in combination with a simple, yet efficient data term compression, can cope with high-resolution data. The incorporation of SIFT (Scale-Invariant Feature Transform) features into data term computation further resolves matching ambiguities, making long-range correspondence estimation possible. We detect occluded areas by evaluating the correspondence symmetry, we further apply Geodesic matting to automatically determine plausible values in these regions. |
Subject | Belief Propagation, Dense Image Correspondences, Depth Reconstruction, Optical Flow, Video Post-Production |
Classified Subjects |
|
DDC | 004 |
Rights | DPPL |
URN: | urn:nbn:de:0009-6-35543 |
DOI | https://doi.org/10.20385/1860-2037/9.2012.8 |