Saved in:
Bibliographic Details
Main Authors: Deng, Junli, Luo, Yihao
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.00333
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915132121022464
author Deng, Junli
Luo, Yihao
author_facet Deng, Junli
Luo, Yihao
contents Dynamic scene rendering has taken a leap forward with the rise of 4D Gaussian Splatting, but there's 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 unveil a fresh approach that blends state-space modeling with Wasserstein geometry, paving the way for 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 stay true to their way over time. We also employ Wasserstein distance regularization 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 physically plausible model for dynamic scenes. Our approach guides Gaussians along their natural way in the Wasserstein space, achieving smoother, more realistic motion and stronger temporal coherence. Experimental results show significant improvements in rendering quality and efficiency, outperforming current state-of-the-art techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2412_00333
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Gaussians on their Way: Wasserstein-Constrained 4D Gaussian Splatting with State-Space Modeling
Deng, Junli
Luo, Yihao
Computer Vision and Pattern Recognition
Dynamic scene rendering has taken a leap forward with the rise of 4D Gaussian Splatting, but there's 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 unveil a fresh approach that blends state-space modeling with Wasserstein geometry, paving the way for 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 stay true to their way over time. We also employ Wasserstein distance regularization 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 physically plausible model for dynamic scenes. Our approach guides Gaussians along their natural way in the Wasserstein space, achieving smoother, more realistic motion and stronger temporal coherence. Experimental results show significant improvements in rendering quality and efficiency, outperforming current state-of-the-art techniques.
title Gaussians on their Way: Wasserstein-Constrained 4D Gaussian Splatting with State-Space Modeling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.00333