D-MiSo: Editing Dynamic 3D Scenes using Multi-Gaussians Soup

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Waczyńska, Joanna, Borycki, Piotr, Kaleta, Joanna, Tadeja, Sławomir, Spurek, Przemysław
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915046423003136
author Waczyńska, Joanna
Borycki, Piotr
Kaleta, Joanna
Tadeja, Sławomir
Spurek, Przemysław
author_facet Waczyńska, Joanna
Borycki, Piotr
Kaleta, Joanna
Tadeja, Sławomir
Spurek, Przemysław
contents Over the past years, we have observed an abundance of approaches for modeling dynamic 3D scenes using Gaussian Splatting (GS). Such solutions use GS to represent the scene's structure and the neural network to model dynamics. Such approaches allow fast rendering and extracting each element of such a dynamic scene. However, modifying such objects over time is challenging. SC-GS (Sparse Controlled Gaussian Splatting) enhanced with Deformed Control Points partially solves this issue. However, this approach necessitates selecting elements that need to be kept fixed, as well as centroids that should be adjusted throughout editing. Moreover, this task poses additional difficulties regarding the re-productivity of such editing. To address this, we propose Dynamic Multi-Gaussian Soup (D-MiSo), which allows us to model the mesh-inspired representation of dynamic GS. Additionally, we propose a strategy of linking parameterized Gaussian splats, forming a Triangle Soup with the estimated mesh. Consequently, we can separately construct new trajectories for the 3D objects composing the scene. Thus, we can make the scene's dynamic editable over time or while maintaining partial dynamics.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14276
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle D-MiSo: Editing Dynamic 3D Scenes using Multi-Gaussians Soup
Waczyńska, Joanna
Borycki, Piotr
Kaleta, Joanna
Tadeja, Sławomir
Spurek, Przemysław
Computer Vision and Pattern Recognition
Over the past years, we have observed an abundance of approaches for modeling dynamic 3D scenes using Gaussian Splatting (GS). Such solutions use GS to represent the scene's structure and the neural network to model dynamics. Such approaches allow fast rendering and extracting each element of such a dynamic scene. However, modifying such objects over time is challenging. SC-GS (Sparse Controlled Gaussian Splatting) enhanced with Deformed Control Points partially solves this issue. However, this approach necessitates selecting elements that need to be kept fixed, as well as centroids that should be adjusted throughout editing. Moreover, this task poses additional difficulties regarding the re-productivity of such editing. To address this, we propose Dynamic Multi-Gaussian Soup (D-MiSo), which allows us to model the mesh-inspired representation of dynamic GS. Additionally, we propose a strategy of linking parameterized Gaussian splats, forming a Triangle Soup with the estimated mesh. Consequently, we can separately construct new trajectories for the 3D objects composing the scene. Thus, we can make the scene's dynamic editable over time or while maintaining partial dynamics.
title D-MiSo: Editing Dynamic 3D Scenes using Multi-Gaussians Soup
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.14276