Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Zhenwei, Wang, Tengfei, He, Zexin, Hancke, Gerhard, Liu, Ziwei, Lau, Rynson W. H.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929502349688832
author Wang, Zhenwei
Wang, Tengfei
He, Zexin
Hancke, Gerhard
Liu, Ziwei
Lau, Rynson W. H.
author_facet Wang, Zhenwei
Wang, Tengfei
He, Zexin
Hancke, Gerhard
Liu, Ziwei
Lau, Rynson W. H.
contents In 3D modeling, designers often use an existing 3D model as a reference to create new ones. This practice has inspired the development of Phidias, a novel generative model that uses diffusion for reference-augmented 3D generation. Given an image, our method leverages a retrieved or user-provided 3D reference model to guide the generation process, thereby enhancing the generation quality, generalization ability, and controllability. Our model integrates three key components: 1) meta-ControlNet that dynamically modulates the conditioning strength, 2) dynamic reference routing that mitigates misalignment between the input image and 3D reference, and 3) self-reference augmentations that enable self-supervised training with a progressive curriculum. Collectively, these designs result in a clear improvement over existing methods. Phidias establishes a unified framework for 3D generation using text, image, and 3D conditions with versatile applications.
format Preprint
id arxiv_https___arxiv_org_abs_2409_11406
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion
Wang, Zhenwei
Wang, Tengfei
He, Zexin
Hancke, Gerhard
Liu, Ziwei
Lau, Rynson W. H.
Computer Vision and Pattern Recognition
In 3D modeling, designers often use an existing 3D model as a reference to create new ones. This practice has inspired the development of Phidias, a novel generative model that uses diffusion for reference-augmented 3D generation. Given an image, our method leverages a retrieved or user-provided 3D reference model to guide the generation process, thereby enhancing the generation quality, generalization ability, and controllability. Our model integrates three key components: 1) meta-ControlNet that dynamically modulates the conditioning strength, 2) dynamic reference routing that mitigates misalignment between the input image and 3D reference, and 3) self-reference augmentations that enable self-supervised training with a progressive curriculum. Collectively, these designs result in a clear improvement over existing methods. Phidias establishes a unified framework for 3D generation using text, image, and 3D conditions with versatile applications.
title Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.11406