RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion

We introduce RealmDreamer, a technique for generation of general forward-facing 3D scenes from text descriptions. Our technique optimizes a 3D Gaussian Splatting representation to match complex text prompts. We initialize these splats by utilizing the state-of-the-art text-to-image generators, lifti...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Jaidev Shriram, Trevithick, Alex, Liu, Lingjie, Ramamoorthi, Ravi
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 10.04.2024
Subjects
Image processors
Occlusion
Representations
Scene generation
Online AccessGet full text

Cover

More Information
Summary:We introduce RealmDreamer, a technique for generation of general forward-facing 3D scenes from text descriptions. Our technique optimizes a 3D Gaussian Splatting representation to match complex text prompts. We initialize these splats by utilizing the state-of-the-art text-to-image generators, lifting their samples into 3D, and computing the occlusion volume. We then optimize this representation across multiple views as a 3D inpainting task with image-conditional diffusion models. To learn correct geometric structure, we incorporate a depth diffusion model by conditioning on the samples from the inpainting model, giving rich geometric structure. Finally, we finetune the model using sharpened samples from image generators. Notably, our technique does not require video or multi-view data and can synthesize a variety of high-quality 3D scenes in different styles, consisting of multiple objects. Its generality additionally allows 3D synthesis from a single image.
ISSN:2331-8422