Citation and metadata
Recommended citation
Christian Kurz, Tobias Ritschel, Elmar Eisemann, Thorsten Thormählen, and Hans-Peter Seidel, Generating Realistic Camera Shake for Virtual Scenes. JVRB - Journal of Virtual Reality and Broadcasting, 10(2013), no. 7. (urn:nbn:de:0009-6-38335)
Download Citation
Endnote
%0 Journal Article %T Generating Realistic Camera Shake for Virtual Scenes %A Kurz, Christian %A Ritschel, Tobias %A Eisemann, Elmar %A Thormählen, Thorsten %A Seidel, Hans-Peter %J JVRB - Journal of Virtual Reality and Broadcasting %D 2014 %V 10(2013) %N 7 %@ 1860-2037 %F kurz2014 %X When depicting both virtual and physical worlds, the viewer's impression of presence in these worldsis strongly linked to camera motion. Plausible and artist-controlled camera movement can substantiallyincrease scene immersion. While physical camera motion exhibits subtle details of position, rotation,and acceleration, these details are often missing for virtual camera motion. In this work, we analyze camera movement using signal theory. Our system allows us to stylize a smooth user-defined virtual base camera motion by enriching it with plausible details. A key component of our system is a database of videos filmed by physical cameras. These videos are analyzed with a camera-motion estimation algorithm (structure-from-motion) and labeled manually with a specific style. By considering spectral properties of location, orientation and acceleration, our solution learns camera motion details. Consequently, an arbitrary virtual base motion, defined in any conventional animation package, can be automatically modified according to a user-selected style. In an animation package the camera motion base path is typically defined by the user via function curves. Another possibility is to obtain the camera path by using a mixed reality camera in motion capturing studio. As shown in our experiments, the resulting shots are still fully artist-controlled, but appear richer and more physically plausible. %L 004 %K camera motion estimation %K camera shake %K structure-from-motion %K style transfer %R 10.20385/1860-2037/10.2013.7 %U http://nbn-resolving.de/urn:nbn:de:0009-6-38335 %U http://dx.doi.org/10.20385/1860-2037/10.2013.7Download
Bibtex
@Article{kurz2014, author = "Kurz, Christian and Ritschel, Tobias and Eisemann, Elmar and Thorm{\"a}hlen, Thorsten and Seidel, Hans-Peter", title = "Generating Realistic Camera Shake for Virtual Scenes", journal = "JVRB - Journal of Virtual Reality and Broadcasting", year = "2014", volume = "10(2013)", number = "7", keywords = "camera motion estimation; camera shake; structure-from-motion; style transfer", abstract = "When depicting both virtual and physical worlds, the viewer's impression of presence in these worldsis strongly linked to camera motion. Plausible and artist-controlled camera movement can substantiallyincrease scene immersion. While physical camera motion exhibits subtle details of position, rotation,and acceleration, these details are often missing for virtual camera motion. In this work, we analyze camera movement using signal theory. Our system allows us to stylize a smooth user-defined virtual base camera motion by enriching it with plausible details. A key component of our system is a database of videos filmed by physical cameras. These videos are analyzed with a camera-motion estimation algorithm (structure-from-motion) and labeled manually with a specific style. By considering spectral properties of location, orientation and acceleration, our solution learns camera motion details. Consequently, an arbitrary virtual base motion, defined in any conventional animation package, can be automatically modified according to a user-selected style. In an animation package the camera motion base path is typically defined by the user via function curves. Another possibility is to obtain the camera path by using a mixed reality camera in motion capturing studio. As shown in our experiments, the resulting shots are still fully artist-controlled, but appear richer and more physically plausible.", issn = "1860-2037", doi = "10.20385/1860-2037/10.2013.7", url = "http://nbn-resolving.de/urn:nbn:de:0009-6-38335" }Download
RIS
TY - JOUR AU - Kurz, Christian AU - Ritschel, Tobias AU - Eisemann, Elmar AU - Thormählen, Thorsten AU - Seidel, Hans-Peter PY - 2014 DA - 2014// TI - Generating Realistic Camera Shake for Virtual Scenes JO - JVRB - Journal of Virtual Reality and Broadcasting VL - 10(2013) IS - 7 KW - camera motion estimation KW - camera shake KW - structure-from-motion KW - style transfer AB - When depicting both virtual and physical worlds, the viewer's impression of presence in these worldsis strongly linked to camera motion. Plausible and artist-controlled camera movement can substantiallyincrease scene immersion. While physical camera motion exhibits subtle details of position, rotation,and acceleration, these details are often missing for virtual camera motion. In this work, we analyze camera movement using signal theory. Our system allows us to stylize a smooth user-defined virtual base camera motion by enriching it with plausible details. A key component of our system is a database of videos filmed by physical cameras. These videos are analyzed with a camera-motion estimation algorithm (structure-from-motion) and labeled manually with a specific style. By considering spectral properties of location, orientation and acceleration, our solution learns camera motion details. Consequently, an arbitrary virtual base motion, defined in any conventional animation package, can be automatically modified according to a user-selected style. In an animation package the camera motion base path is typically defined by the user via function curves. Another possibility is to obtain the camera path by using a mixed reality camera in motion capturing studio. As shown in our experiments, the resulting shots are still fully artist-controlled, but appear richer and more physically plausible. SN - 1860-2037 UR - http://nbn-resolving.de/urn:nbn:de:0009-6-38335 DO - 10.20385/1860-2037/10.2013.7 ID - kurz2014 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>kurz2014</b:Tag> <b:SourceType>ArticleInAPeriodical</b:SourceType> <b:Year>2014</b:Year> <b:PeriodicalTitle>JVRB - Journal of Virtual Reality and Broadcasting</b:PeriodicalTitle> <b:Volume>10(2013)</b:Volume> <b:Issue>7</b:Issue> <b:Url>http://nbn-resolving.de/urn:nbn:de:0009-6-38335</b:Url> <b:Url>http://dx.doi.org/10.20385/1860-2037/10.2013.7</b:Url> <b:Author> <b:Author><b:NameList> <b:Person><b:Last>Kurz</b:Last><b:First>Christian</b:First></b:Person> <b:Person><b:Last>Ritschel</b:Last><b:First>Tobias</b:First></b:Person> <b:Person><b:Last>Eisemann</b:Last><b:First>Elmar</b:First></b:Person> <b:Person><b:Last>Thormählen</b:Last><b:First>Thorsten</b:First></b:Person> <b:Person><b:Last>Seidel</b:Last><b:First>Hans-Peter</b:First></b:Person> </b:NameList></b:Author> </b:Author> <b:Title>Generating Realistic Camera Shake for Virtual Scenes</b:Title> <b:Comments>When depicting both virtual and physical worlds, the viewer's impression of presence in these worldsis strongly linked to camera motion. Plausible and artist-controlled camera movement can substantiallyincrease scene immersion. While physical camera motion exhibits subtle details of position, rotation,and acceleration, these details are often missing for virtual camera motion. In this work, we analyze camera movement using signal theory. Our system allows us to stylize a smooth user-defined virtual base camera motion by enriching it with plausible details. A key component of our system is a database of videos filmed by physical cameras. These videos are analyzed with a camera-motion estimation algorithm (structure-from-motion) and labeled manually with a specific style. By considering spectral properties of location, orientation and acceleration, our solution learns camera motion details. Consequently, an arbitrary virtual base motion, defined in any conventional animation package, can be automatically modified according to a user-selected style. In an animation package the camera motion base path is typically defined by the user via function curves. Another possibility is to obtain the camera path by using a mixed reality camera in motion capturing studio. As shown in our experiments, the resulting shots are still fully artist-controlled, but appear richer and more physically plausible.</b:Comments> </b:Source> </b:Sources>Download
ISI
PT Journal AU Kurz, C Ritschel, T Eisemann, E Thormählen, T Seidel, H TI Generating Realistic Camera Shake for Virtual Scenes SO JVRB - Journal of Virtual Reality and Broadcasting PY 2014 VL 10(2013) IS 7 DI 10.20385/1860-2037/10.2013.7 DE camera motion estimation; camera shake; structure-from-motion; style transfer AB When depicting both virtual and physical worlds, the viewer's impression of presence in these worldsis strongly linked to camera motion. Plausible and artist-controlled camera movement can substantiallyincrease scene immersion. While physical camera motion exhibits subtle details of position, rotation,and acceleration, these details are often missing for virtual camera motion. In this work, we analyze camera movement using signal theory. Our system allows us to stylize a smooth user-defined virtual base camera motion by enriching it with plausible details. A key component of our system is a database of videos filmed by physical cameras. These videos are analyzed with a camera-motion estimation algorithm (structure-from-motion) and labeled manually with a specific style. By considering spectral properties of location, orientation and acceleration, our solution learns camera motion details. Consequently, an arbitrary virtual base motion, defined in any conventional animation package, can be automatically modified according to a user-selected style. In an animation package the camera motion base path is typically defined by the user via function curves. Another possibility is to obtain the camera path by using a mixed reality camera in motion capturing studio. As shown in our experiments, the resulting shots are still fully artist-controlled, but appear richer and more physically plausible. ERDownload
Mods
<mods> <titleInfo> <title>Generating Realistic Camera Shake for Virtual Scenes</title> </titleInfo> <name type="personal"> <namePart type="family">Kurz</namePart> <namePart type="given">Christian</namePart> </name> <name type="personal"> <namePart type="family">Ritschel</namePart> <namePart type="given">Tobias</namePart> </name> <name type="personal"> <namePart type="family">Eisemann</namePart> <namePart type="given">Elmar</namePart> </name> <name type="personal"> <namePart type="family">Thormählen</namePart> <namePart type="given">Thorsten</namePart> </name> <name type="personal"> <namePart type="family">Seidel</namePart> <namePart type="given">Hans-Peter</namePart> </name> <abstract>When depicting both virtual and physical worlds, the viewer's impression of presence in these worlds is strongly linked to camera motion. Plausible and artist-controlled camera movement can substantially increase scene immersion. While physical camera motion exhibits subtle details of position, rotation, and acceleration, these details are often missing for virtual camera motion. In this work, we analyze camera movement using signal theory. Our system allows us to stylize a smooth user-defined virtual base camera motion by enriching it with plausible details. A key component of our system is a database of videos filmed by physical cameras. These videos are analyzed with a camera-motion estimation algorithm (structure-from-motion) and labeled manually with a specific style. By considering spectral properties of location, orientation and acceleration, our solution learns camera motion details. Consequently, an arbitrary virtual base motion, defined in any conventional animation package, can be automatically modified according to a user-selected style. In an animation package the camera motion base path is typically defined by the user via function curves. Another possibility is to obtain the camera path by using a mixed reality camera in motion capturing studio. As shown in our experiments, the resulting shots are still fully artist-controlled, but appear richer and more physically plausible.</abstract> <subject> <topic>camera motion estimation</topic> <topic>camera shake</topic> <topic>structure-from-motion</topic> <topic>style transfer</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>10(2013)</number> </detail> <detail type="issue"> <number>7</number> </detail> <date>2014</date> </part> </relatedItem> <identifier type="issn">1860-2037</identifier> <identifier type="urn">urn:nbn:de:0009-6-38335</identifier> <identifier type="doi">10.20385/1860-2037/10.2013.7</identifier> <identifier type="uri">http://nbn-resolving.de/urn:nbn:de:0009-6-38335</identifier> <identifier type="citekey">kurz2014</identifier> </mods>Download
Full Metadata
Bibliographic Citation | JVRB, 10(2013), no. 7. |
---|---|
Title |
Generating Realistic Camera Shake for Virtual Scenes (eng) |
Author | Christian Kurz, Tobias Ritschel, Elmar Eisemann, Thorsten Thormählen, Hans-Peter Seidel |
Language | eng |
Abstract | When depicting both virtual and physical worlds, the viewer's impression of presence in these worlds is strongly linked to camera motion. Plausible and artist-controlled camera movement can substantially increase scene immersion. While physical camera motion exhibits subtle details of position, rotation, and acceleration, these details are often missing for virtual camera motion. In this work, we analyze camera movement using signal theory. Our system allows us to stylize a smooth user-defined virtual base camera motion by enriching it with plausible details. A key component of our system is a database of videos filmed by physical cameras. These videos are analyzed with a camera-motion estimation algorithm (structure-from-motion) and labeled manually with a specific style. By considering spectral properties of location, orientation and acceleration, our solution learns camera motion details. Consequently, an arbitrary virtual base motion, defined in any conventional animation package, can be automatically modified according to a user-selected style. In an animation package the camera motion base path is typically defined by the user via function curves. Another possibility is to obtain the camera path by using a mixed reality camera in motion capturing studio. As shown in our experiments, the resulting shots are still fully artist-controlled, but appear richer and more physically plausible. |
Subject | camera motion estimation, camera shake, structure-from-motion, style transfer |
Classified Subjects |
|
DDC | 004 |
Rights | DPPL |
URN: | urn:nbn:de:0009-6-38335 |
DOI | https://doi.org/10.20385/1860-2037/10.2013.7 |