Year: 2023
Type: preprint
Abstract: We present our method for transferring style from any arbitrary image(s) to object(s) within a 3D scene. Our primary objective is to offer more control in 3D scene stylization, facilitating the creation of customizable and stylized scene images from arbitrary viewpoints. To achieve this, we propose a novel approach that incorporates nearest neighborhood-based loss, allowing for flexible 3D scene reconstruction while effectively capturing intricate style details and ensuring multi-view consistency.
Source: arXiv (Cornell University)
Authors: Lahiri, Dishani, Panse, Neeraj, Kumar, Moneish
Institution: Carnegie Mellon University
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4386501544