FlowCapX: Physics-Grounded Flow Capture with Long-Term Consistency

dc.contributor.authorTao, Ningxiaoen_US
dc.contributor.authorZhang, Liruen_US
dc.contributor.authorNi, Xingyuen_US
dc.contributor.authorChu, Mengyuen_US
dc.contributor.authorChen, Baoquanen_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.date.accessioned2025-10-07T05:03:42Z
dc.date.available2025-10-07T05:03:42Z
dc.date.issued2025
dc.description.abstractWe present FlowCapX, a physics-enhanced framework for flow reconstruction from sparse video inputs, addressing the challenge of jointly optimizing complex physical constraints and sparse observational data over long time horizons. Existing methods often struggle to capture turbulent motion while maintaining physical consistency, limiting reconstruction quality and downstream tasks. Focusing on velocity inference, our approach introduces a hybrid framework that strategically separates representation and supervision across spatial scales. At the coarse level, we resolve sparse-view ambiguities via a novel optimization strategy that aligns long-term observation with physics-grounded velocity fields. By emphasizing vorticity-based physical constraints, our method enhances physical fidelity and improves optimization stability. At the fine level, we prioritize observational fidelity to preserve critical turbulent structures. Extensive experiments demonstrate state-of-the-art velocity reconstruction, enabling velocity-aware downstream tasks, e.g., accurate flow analysis, scene augmentation with tracer visualization and re-simulation. Our implementation is released at https://github.com/taoningxiao/FlowCapX.git.en_US
dc.description.number7
dc.description.sectionheadersDetecting & Estimating from images and videos
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70274
dc.identifier.issn1467-8659
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70274
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70274
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Physical simulation; Neural networks
dc.subjectComputing methodologies → Physical simulation
dc.subjectNeural networks
dc.titleFlowCapX: Physics-Grounded Flow Capture with Long-Term Consistencyen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
cgf70274.pdf
Size:
10.95 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
paper1137_mm.zip
Size:
340.76 MB
Format:
Zip file
Collections