MaGRITTe: Manipulative and Generative 3D Realization from Image, Topview and Text

arXiv:2404.00345v1 Announce Type: new
Abstract: The generation of 3D scenes from user-specified conditions offers a promising avenue for alleviating the production burden in 3D applications. Previous studies required significant effort to realize the desired scene, owing to limited control conditions. We propose a method for controlling and generating 3D scenes under multimodal conditions using partial images, layout information represented in the top view, and text prompts. Combining these conditions to generate a 3D scene involves the following significant difficulties: (1) …

3d scenes abstract applications arxiv control cs.cv generative image production studies text type