BoLeRO: A Principled Technique for Including Bone Length Constraints in Motion Capture Occlusion Filling

dc.contributor.authorLi, Leien_US
dc.contributor.authorMcCann, Jamesen_US
dc.contributor.authorPollard, Nancyen_US
dc.contributor.authorFaloutsos, Christosen_US
dc.contributor.editorMZoran Popovic and Miguel Otaduyen_US
dc.date.accessioned2014-01-29T07:51:32Z
dc.date.available2014-01-29T07:51:32Z
dc.date.issued2010en_US
dc.description.abstractGiven a motion capture sequence with occlusions, how can we recover the missing values, respecting bone-length constraints? Recent past work uses Linear Dynamical Systems (LDS), which work well, except for occasionally violating such constraints, and thus lead to unrealistic results. Our main contribution is a principled approach for preserving such distances. Specifically (a) we show how to formulate the problem as a constrained optimization problem, using two variations: hard constraints, and soft constraints; (b) we show how to efficiently solve both variations; (c) we demonstrate the realism of our approaches against competitors, on real motion capture data, illustrating that our 'soft constraints' version eventually produces more realistic resultsen_US
dc.description.seriesinformationEurographics/ ACM SIGGRAPH Symposium on Computer Animationen_US
dc.identifier.isbn978-3-905674-27-9en_US
dc.identifier.issn1727-5288en_US
dc.identifier.urihttps://doi.org/10.2312/SCA/SCA10/179-188en_US
dc.publisherThe Eurographics Associationen_US
dc.titleBoLeRO: A Principled Technique for Including Bone Length Constraints in Motion Capture Occlusion Fillingen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
179-188.pdf
Size:
194.25 KB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
bolero-final-v1.mp4
Size:
20.95 MB
Format:
Unknown data format