Saved in:
Bibliographic Details
Main Authors: Oztas, Ipek, Ceylan, Duygu, Dundar, Aysegul
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.21836
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918005487697920
author Oztas, Ipek
Ceylan, Duygu
Dundar, Aysegul
author_facet Oztas, Ipek
Ceylan, Duygu
Dundar, Aysegul
contents With the growing success of text or image guided 3D generators, users demand more control over the generation process, appearance stylization being one of them. Given a reference image, this requires adapting the appearance of a generated 3D asset to reflect the visual style of the reference while maintaining visual consistency from multiple viewpoints. To tackle this problem, we draw inspiration from the success of 2D stylization methods that leverage the attention mechanisms in large image generation models to capture and transfer visual style. In particular, we probe if large reconstruction models, commonly used in the context of 3D generation, has a similar capability. We discover that the certain attention blocks in these models capture the appearance specific features. By injecting features from a visual style image to such blocks, we develop a simple yet effective 3D appearance stylization method. Our method does not require training or test time optimization. Through both quantitative and qualitative evaluations, we demonstrate that our approach achieves superior results in terms of 3D appearance stylization, significantly improving efficiency while maintaining high-quality visual outcomes.
format Preprint
id arxiv_https___arxiv_org_abs_2504_21836
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle 3D Stylization via Large Reconstruction Model
Oztas, Ipek
Ceylan, Duygu
Dundar, Aysegul
Computer Vision and Pattern Recognition
With the growing success of text or image guided 3D generators, users demand more control over the generation process, appearance stylization being one of them. Given a reference image, this requires adapting the appearance of a generated 3D asset to reflect the visual style of the reference while maintaining visual consistency from multiple viewpoints. To tackle this problem, we draw inspiration from the success of 2D stylization methods that leverage the attention mechanisms in large image generation models to capture and transfer visual style. In particular, we probe if large reconstruction models, commonly used in the context of 3D generation, has a similar capability. We discover that the certain attention blocks in these models capture the appearance specific features. By injecting features from a visual style image to such blocks, we develop a simple yet effective 3D appearance stylization method. Our method does not require training or test time optimization. Through both quantitative and qualitative evaluations, we demonstrate that our approach achieves superior results in terms of 3D appearance stylization, significantly improving efficiency while maintaining high-quality visual outcomes.
title 3D Stylization via Large Reconstruction Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.21836