Differentiable Depth for Real2Sim Calibration of Soft Body Simulations

dc.contributor.authorArnavaz, K.en_US
dc.contributor.authorNielsen, M. Kragballeen_US
dc.contributor.authorKry, P. G.en_US
dc.contributor.authorMacklin, M.en_US
dc.contributor.authorErleben, K.en_US
dc.contributor.editorHauser, Helwig and Alliez, Pierreen_US
dc.date.accessioned2023-03-22T15:07:15Z
dc.date.available2023-03-22T15:07:15Z
dc.date.issued2023
dc.description.abstractIn this work, we present a novel approach for calibrating material model parameters for soft body simulations using real data. We use a fully differentiable pipeline, combining a differentiable soft body simulator and differentiable depth rendering, which permits fast gradient‐based optimizations. Our method requires no data pre‐processing, and minimal experimental set‐up, as we directly minimize the L2‐norm between raw LIDAR scans and rendered simulation states. In essence, we provide the first marker‐free approach for calibrating a soft‐body simulator to match observed real‐world deformations. Our approach is inexpensive as it solely requires a consumer‐level LIDAR sensor compared to acquiring a professional marker‐based motion capture system. We investigate the effects of different material parameterizations and evaluate convergence for parameter optimization in both single and multi‐material scenarios of varying complexity. Finally, we show that our set‐up can be extended to optimize for dynamic behaviour as well.en_US
dc.description.number1
dc.description.sectionheadersMajor Revision from Eurographics Conference
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume42
dc.identifier.doi10.1111/cgf.14720
dc.identifier.issn1467-8659
dc.identifier.pages277-289
dc.identifier.urihttps://doi.org/10.1111/cgf.14720
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14720
dc.publisherEurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectanimation
dc.subjectphysically based animation
dc.subjectmethods and applications
dc.subjectrobotics
dc.subjectrendering
dc.subjectray tracing
dc.titleDifferentiable Depth for Real2Sim Calibration of Soft Body Simulationsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
v42i1pp277-289-cgf14720.pdf
Size:
3.56 MB
Format:
Adobe Portable Document Format
Collections