ContactVision: Learning Foot Contact from Video for Physically Plausible Gait Animation

Simple item page
dc.contributor.authorKim, Daeyong
dc.contributor.authorYi, Gyuseok
dc.contributor.authorYu, Ri
dc.contributor.editorMasia, Belen
dc.contributor.editorThies, Justus
dc.date.accessioned2026-04-17T09:37:53Z
dc.date.available2026-04-17T09:37:53Z
dc.date.issued2026
dc.description.abstractFoot-ground contact information plays a crucial role in character animation and gait analysis, as it helps accurately simulating realistic movement patterns and understanding the biomechanics of walking. Existing motion datasets do not explicitly include foot-ground contact information, requiring separate computation or manual annotation. Obtaining accurate foot-ground contact information typically requires additional sensors such as pressure mats or force plates. Without such devices, estimating contact becomes a highly challenging task. We propose ContactVision, a deep learning framework that detects heel and toe contact states directly from video. Our network is trained in a supervised manner using contact labels derived from motion capture data via ground reaction force estimation. This enables training on existing datasets without the need for additional hardware. We demonstrate the utility of our contact detection network in two downstream tasks: gait motion reconstruction and gait analysis. For animation, we incorporate predicted contact labels into a reinforcement learning framework with a twosegment foot model, enabling realistic foot articulation behavior. For analysis, we estimate clinically relevant gait parameters such as double and single support times, and validate the accuracy against pressure sensor mat data and prior video-based methods. Our results show competitive performance in both animation and analysis settings. The code is publicly available at github.com/DaeeYong/ContactVision.
dc.description.number2
dc.description.sectionheadersMotion in the Wild: From Individuals to Crowds
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume45
dc.identifier.doi10.1111/cgf.70334
dc.identifier.issn1467-8659
dc.identifier.pages17 pages
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70334
dc.identifier.urihttps://doi.org/10.1111/cgf334
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.
dc.rightsCC-BY-4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectfoot-ground contact detection, video processing, motion reconstruction, gait analysis
dc.subjectfoot-ground contact detection
dc.subjectvideo processing
dc.subjectmotion reconstruction
dc.subjectgait analysis
dc.subjectComputing methodologies → Motion processing
dc.subjectAnimation
dc.titleContactVision: Learning Foot Contact from Video for Physically Plausible Gait Animation
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
cgf70334.pdf
Size:
24.09 MB
Format:
Adobe Portable Document Format
Download
Collections
45-Issue 2
EG 2026 - Full Papers - CGF 45-Issue 2