English

AI-Driven Stylization of 3D Environments

Computer Vision and Pattern Recognition 2024-11-12 v1 Graphics

Abstract

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.

Keywords

Cite

@article{arxiv.2411.06067,
  title  = {AI-Driven Stylization of 3D Environments},
  author = {Yuanbo Chen and Yixiao Kang and Yukun Song and Cyrus Vachha and Sining Huang},
  journal= {arXiv preprint arXiv:2411.06067},
  year   = {2024}
}
R2 v1 2026-06-28T19:54:03.108Z