Sharp-It: A Multi-view to Multi-view Diffusion Model for 3D Synthesis and Manipulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Edelstein, Yiftach, Patashnik, Or, Cohen-Bar, Dana, Zelnik-Manor, Lihi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912142459928576
author Edelstein, Yiftach
Patashnik, Or
Cohen-Bar, Dana
Zelnik-Manor, Lihi
author_facet Edelstein, Yiftach
Patashnik, Or
Cohen-Bar, Dana
Zelnik-Manor, Lihi
contents Advancements in text-to-image diffusion models have led to significant progress in fast 3D content creation. One common approach is to generate a set of multi-view images of an object, and then reconstruct it into a 3D model. However, this approach bypasses the use of a native 3D representation of the object and is hence prone to geometric artifacts and limited in controllability and manipulation capabilities. An alternative approach involves native 3D generative models that directly produce 3D representations. These models, however, are typically limited in their resolution, resulting in lower quality 3D objects. In this work, we bridge the quality gap between methods that directly generate 3D representations and ones that reconstruct 3D objects from multi-view images. We introduce a multi-view to multi-view diffusion model called Sharp-It, which takes a 3D consistent set of multi-view images rendered from a low-quality object and enriches its geometric details and texture. The diffusion model operates on the multi-view set in parallel, in the sense that it shares features across the generated views. A high-quality 3D model can then be reconstructed from the enriched multi-view set. By leveraging the advantages of both 2D and 3D approaches, our method offers an efficient and controllable method for high-quality 3D content creation. We demonstrate that Sharp-It enables various 3D applications, such as fast synthesis, editing, and controlled generation, while attaining high-quality assets.
format Preprint
id arxiv_https___arxiv_org_abs_2412_02631
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sharp-It: A Multi-view to Multi-view Diffusion Model for 3D Synthesis and Manipulation
Edelstein, Yiftach
Patashnik, Or
Cohen-Bar, Dana
Zelnik-Manor, Lihi
Computer Vision and Pattern Recognition
Machine Learning
Advancements in text-to-image diffusion models have led to significant progress in fast 3D content creation. One common approach is to generate a set of multi-view images of an object, and then reconstruct it into a 3D model. However, this approach bypasses the use of a native 3D representation of the object and is hence prone to geometric artifacts and limited in controllability and manipulation capabilities. An alternative approach involves native 3D generative models that directly produce 3D representations. These models, however, are typically limited in their resolution, resulting in lower quality 3D objects. In this work, we bridge the quality gap between methods that directly generate 3D representations and ones that reconstruct 3D objects from multi-view images. We introduce a multi-view to multi-view diffusion model called Sharp-It, which takes a 3D consistent set of multi-view images rendered from a low-quality object and enriches its geometric details and texture. The diffusion model operates on the multi-view set in parallel, in the sense that it shares features across the generated views. A high-quality 3D model can then be reconstructed from the enriched multi-view set. By leveraging the advantages of both 2D and 3D approaches, our method offers an efficient and controllable method for high-quality 3D content creation. We demonstrate that Sharp-It enables various 3D applications, such as fast synthesis, editing, and controlled generation, while attaining high-quality assets.
title Sharp-It: A Multi-view to Multi-view Diffusion Model for 3D Synthesis and Manipulation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2412.02631