Gaussians on their Way: Wasserstein-Constrained 4D Gaussian Splatting with State-Space Modeling

dc.contributor.authorDeng, Junlien_US
dc.contributor.author, Ping Shien_US
dc.contributor.authorLuo, Yihaoen_US
dc.contributor.authorLi, Qipeien_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.date.accessioned2025-10-07T05:03:34Z
dc.date.available2025-10-07T05:03:34Z
dc.date.issued2025
dc.description.abstractDynamic scene rendering has taken a leap forward with the rise of 4D Gaussian Splatting, but there is still one elusive challenge: how to make 3D Gaussians move through time as naturally as they would in the real world, all while keeping the motion smooth and consistent. In this paper, we present an approach that blends state-space modeling with Wasserstein geometry, enabling a more fluid and coherent representation of dynamic scenes. We introduce a State Consistency Filter that merges prior predictions with the current observations, enabling Gaussians to maintain coherent trajectories over time. We also employ Wasserstein Consistency Constraint to ensure smooth, consistent updates of Gaussian parameters, reducing motion artifacts. Lastly, we leverage Wasserstein geometry to capture both translational motion and shape deformations, creating a more geometrically consistent model for dynamic scenes. Our approach models the evolution of Gaussians along geodesics on the manifold of Gaussian distributions, achieving smoother, more realistic motion and stronger temporal coherence. Experimental results show consistent improvements in rendering quality and efficiency.en_US
dc.description.number7
dc.description.sectionheadersGaussian Splatting
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70271
dc.identifier.issn1467-8659
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70271
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70271
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Rendering; Point-based models; Reconstruction
dc.subjectComputing methodologies → Rendering
dc.subjectPoint
dc.subjectbased models
dc.subjectReconstruction
dc.titleGaussians on their Way: Wasserstein-Constrained 4D Gaussian Splatting with State-Space Modelingen_US
Files
Original bundle
Now showing 1 - 3 of 3
Loading...
Thumbnail Image
Name:
cgf70271.pdf
Size:
8.14 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
paper1279_mm1.zip
Size:
148.77 MB
Format:
Zip file
Loading...
Thumbnail Image
Name:
paper1279_mm2.pdf
Size:
170.55 KB
Format:
Adobe Portable Document Format
Collections