AI-Driven Stylization of 3D Environments
This work addresses 3D environment stylization for graphics or AI applications, but it appears incremental as it builds on established methods without major breakthroughs.
The paper tackles the problem of stylizing 3D primitive objects into higher fidelity scenes using existing image stylization and image-to-3D generative models in a pipeline, showing results on adding generated objects but without concrete performance numbers.
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.