Saved in:
Bibliographic Details
Main Authors: He, Huiang, Zhao, Shengchu, Huang, Jianwen, Li, Jie, Wu, Jiaqi, Zhang, Hu, Tang, Pei, Zheng, Heliang, Li, Yukun, Jia, Rongfei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.09231
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908951925227520
author He, Huiang
Zhao, Shengchu
Huang, Jianwen
Li, Jie
Wu, Jiaqi
Zhang, Hu
Tang, Pei
Zheng, Heliang
Li, Yukun
Jia, Rongfei
author_facet He, Huiang
Zhao, Shengchu
Huang, Jianwen
Li, Jie
Wu, Jiaqi
Zhang, Hu
Tang, Pei
Zheng, Heliang
Li, Yukun
Jia, Rongfei
contents Although recent advances have improved the quality of 3D texture generation, existing methods still struggle with incomplete texture coverage, cross-view inconsistency, and misalignment between geometry and texture. To address these limitations, we propose Hitem3D 2.0, a multi-view guided native 3D texture generation framework that enhances texture quality through the integration of 2D multi-view generation priors and native 3D texture representations. Hitem3D 2.0 comprises two key components: a multi-view synthesis framework and a native 3D texture generation model. The multi-view generation is built upon a pre-trained image editing backbone and incorporates plug-and-play modules that explicitly promote geometric alignment, cross-view consistency, and illumination uniformity, thereby enabling the synthesis of high-fidelity multi-view images. Conditioned on the generated views and 3D geometry, the native 3D texture generation model projects multi-view textures onto 3D surfaces while plausibly completing textures in unseen regions. Through the integration of multi-view consistency constraints with native 3D texture modeling, Hitem3D 2.0 significantly improves texture completeness, cross-view coherence, and geometric alignment. Experimental results demonstrate that Hitem3D 2.0 outperforms existing methods in terms of texture detail, fidelity, consistency, coherence, and alignment.
format Preprint
id arxiv_https___arxiv_org_abs_2604_09231
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hitem3D 2.0: Multi-View Guided Native 3D Texture Generation
He, Huiang
Zhao, Shengchu
Huang, Jianwen
Li, Jie
Wu, Jiaqi
Zhang, Hu
Tang, Pei
Zheng, Heliang
Li, Yukun
Jia, Rongfei
Computer Vision and Pattern Recognition
Although recent advances have improved the quality of 3D texture generation, existing methods still struggle with incomplete texture coverage, cross-view inconsistency, and misalignment between geometry and texture. To address these limitations, we propose Hitem3D 2.0, a multi-view guided native 3D texture generation framework that enhances texture quality through the integration of 2D multi-view generation priors and native 3D texture representations. Hitem3D 2.0 comprises two key components: a multi-view synthesis framework and a native 3D texture generation model. The multi-view generation is built upon a pre-trained image editing backbone and incorporates plug-and-play modules that explicitly promote geometric alignment, cross-view consistency, and illumination uniformity, thereby enabling the synthesis of high-fidelity multi-view images. Conditioned on the generated views and 3D geometry, the native 3D texture generation model projects multi-view textures onto 3D surfaces while plausibly completing textures in unseen regions. Through the integration of multi-view consistency constraints with native 3D texture modeling, Hitem3D 2.0 significantly improves texture completeness, cross-view coherence, and geometric alignment. Experimental results demonstrate that Hitem3D 2.0 outperforms existing methods in terms of texture detail, fidelity, consistency, coherence, and alignment.
title Hitem3D 2.0: Multi-View Guided Native 3D Texture Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.09231