Lay-A-Scene: Personalized 3D Object Arrangement Using Text-to-Image Priors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rahamim, Ohad, Segev, Hilit, Achituve, Idan, Atzmon, Yuval, Kasten, Yoni, Chechik, Gal
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913376863518720
author Rahamim, Ohad
Segev, Hilit
Achituve, Idan
Atzmon, Yuval
Kasten, Yoni
Chechik, Gal
author_facet Rahamim, Ohad
Segev, Hilit
Achituve, Idan
Atzmon, Yuval
Kasten, Yoni
Chechik, Gal
contents Generating 3D visual scenes is at the forefront of visual generative AI, but current 3D generation techniques struggle with generating scenes with multiple high-resolution objects. Here we introduce Lay-A-Scene, which solves the task of Open-set 3D Object Arrangement, effectively arranging unseen objects. Given a set of 3D objects, the task is to find a plausible arrangement of these objects in a scene. We address this task by leveraging pre-trained text-to-image models. We personalize the model and explain how to generate images of a scene that contains multiple predefined objects without neglecting any of them. Then, we describe how to infer the 3D poses and arrangement of objects from a 2D generated image by finding a consistent projection of objects onto the 2D scene. We evaluate the quality of Lay-A-Scene using 3D objects from Objaverse and human raters and find that it often generates coherent and feasible 3D object arrangements.
format Preprint
id arxiv_https___arxiv_org_abs_2406_00687
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Lay-A-Scene: Personalized 3D Object Arrangement Using Text-to-Image Priors
Rahamim, Ohad
Segev, Hilit
Achituve, Idan
Atzmon, Yuval
Kasten, Yoni
Chechik, Gal
Computer Vision and Pattern Recognition
Generating 3D visual scenes is at the forefront of visual generative AI, but current 3D generation techniques struggle with generating scenes with multiple high-resolution objects. Here we introduce Lay-A-Scene, which solves the task of Open-set 3D Object Arrangement, effectively arranging unseen objects. Given a set of 3D objects, the task is to find a plausible arrangement of these objects in a scene. We address this task by leveraging pre-trained text-to-image models. We personalize the model and explain how to generate images of a scene that contains multiple predefined objects without neglecting any of them. Then, we describe how to infer the 3D poses and arrangement of objects from a 2D generated image by finding a consistent projection of objects onto the 2D scene. We evaluate the quality of Lay-A-Scene using 3D objects from Objaverse and human raters and find that it often generates coherent and feasible 3D object arrangements.
title Lay-A-Scene: Personalized 3D Object Arrangement Using Text-to-Image Priors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.00687