arXiv:2411.06067cs.CVcs.GR2024-11
用AI将3D基础物体转为高保真风格化场景
AI-Driven Stylization of 3D Environments
- 结合图像风格化与3D生成模型，迭代优化3D场景
- 支持在场景中添加生成物体并实现风格统一
- 适合游戏/影视场景快速生成，对细节要求高者
本系统提出一种将3D原始物体场景风格化为更高保真度3D场景的方法，利用NeRFs和3D Gaussian Splatting等新型3D表示。通过整合现有图像风格化系统与图像到3D生成模型，构建了迭代式风格化与物体合成的流水线。实验展示了在场景中添加生成物体的效果，并讨论了当前方法的局限性。
原文摘要 · Abstract (English)
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.
3D生成风格迁移NeRF
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。