AI-Driven Stylization of 3D Environments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yuanbo, Kang, Yixiao, Song, Yukun, Vachha, Cyrus, Huang, Sining
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917832781987840
author Chen, Yuanbo
Kang, Yixiao
Song, Yukun
Vachha, Cyrus
Huang, Sining
author_facet Chen, Yuanbo
Kang, Yixiao
Song, Yukun
Vachha, Cyrus
Huang, Sining
contents In this system, we discuss methods to stylize a scene of 3D primitive objects into a higher fidelity 3D scene using novel 3D representations like NeRFs and 3D Gaussian Splatting. Our approach leverages existing image stylization systems and image-to-3D generative models to create a pipeline that iteratively stylizes and composites 3D objects into scenes. We show our results on adding generated objects into a scene and discuss limitations.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06067
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AI-Driven Stylization of 3D Environments
Chen, Yuanbo
Kang, Yixiao
Song, Yukun
Vachha, Cyrus
Huang, Sining
Computer Vision and Pattern Recognition
Graphics
In this system, we discuss methods to stylize a scene of 3D primitive objects into a higher fidelity 3D scene using novel 3D representations like NeRFs and 3D Gaussian Splatting. Our approach leverages existing image stylization systems and image-to-3D generative models to create a pipeline that iteratively stylizes and composites 3D objects into scenes. We show our results on adding generated objects into a scene and discuss limitations.
title AI-Driven Stylization of 3D Environments
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2411.06067