CoGS: Controllable Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Heng, Julin, Joel, Milacski, Zoltán Á., Niinuma, Koichiro, Jeni, László A.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914763567529984
author Yu, Heng
Julin, Joel
Milacski, Zoltán Á.
Niinuma, Koichiro
Jeni, László A.
author_facet Yu, Heng
Julin, Joel
Milacski, Zoltán Á.
Niinuma, Koichiro
Jeni, László A.
contents Capturing and re-animating the 3D structure of articulated objects present significant barriers. On one hand, methods requiring extensively calibrated multi-view setups are prohibitively complex and resource-intensive, limiting their practical applicability. On the other hand, while single-camera Neural Radiance Fields (NeRFs) offer a more streamlined approach, they have excessive training and rendering costs. 3D Gaussian Splatting would be a suitable alternative but for two reasons. Firstly, existing methods for 3D dynamic Gaussians require synchronized multi-view cameras, and secondly, the lack of controllability in dynamic scenarios. We present CoGS, a method for Controllable Gaussian Splatting, that enables the direct manipulation of scene elements, offering real-time control of dynamic scenes without the prerequisite of pre-computing control signals. We evaluated CoGS using both synthetic and real-world datasets that include dynamic objects that differ in degree of difficulty. In our evaluations, CoGS consistently outperformed existing dynamic and controllable neural representations in terms of visual fidelity.
format Preprint
id arxiv_https___arxiv_org_abs_2312_05664
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle CoGS: Controllable Gaussian Splatting
Yu, Heng
Julin, Joel
Milacski, Zoltán Á.
Niinuma, Koichiro
Jeni, László A.
Computer Vision and Pattern Recognition
Capturing and re-animating the 3D structure of articulated objects present significant barriers. On one hand, methods requiring extensively calibrated multi-view setups are prohibitively complex and resource-intensive, limiting their practical applicability. On the other hand, while single-camera Neural Radiance Fields (NeRFs) offer a more streamlined approach, they have excessive training and rendering costs. 3D Gaussian Splatting would be a suitable alternative but for two reasons. Firstly, existing methods for 3D dynamic Gaussians require synchronized multi-view cameras, and secondly, the lack of controllability in dynamic scenarios. We present CoGS, a method for Controllable Gaussian Splatting, that enables the direct manipulation of scene elements, offering real-time control of dynamic scenes without the prerequisite of pre-computing control signals. We evaluated CoGS using both synthetic and real-world datasets that include dynamic objects that differ in degree of difficulty. In our evaluations, CoGS consistently outperformed existing dynamic and controllable neural representations in terms of visual fidelity.
title CoGS: Controllable Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.05664