CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Chenyu, Chen, Hongze, Bao, Jingzhi, Zhu, Lingting, Zhang, Runze, Chen, Weikai, Hu, Zeyu, Yin, Yingda, Luo, Keyang, Wang, Xin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915646444404736
author Liu, Chenyu
Chen, Hongze
Bao, Jingzhi
Zhu, Lingting
Zhang, Runze
Chen, Weikai
Hu, Zeyu
Yin, Yingda
Luo, Keyang
Wang, Xin
author_facet Liu, Chenyu
Chen, Hongze
Bao, Jingzhi
Zhu, Lingting
Zhang, Runze
Chen, Weikai
Hu, Zeyu
Yin, Yingda
Luo, Keyang
Wang, Xin
contents Despite major advances brought by diffusion-based models, current 3D texture generation systems remain hindered by cross-view inconsistency -- textures that appear convincing from one viewpoint often fail to align across others. We find that this issue arises from attention ambiguity, where unstructured full attention is applied indiscriminately across tokens and modalities, causing geometric confusion and unstable appearance-structure coupling. To address this, we introduce CaliTex, a framework of geometry-calibrated attention that explicitly aligns attention with 3D structure. It introduces two modules: Part-Aligned Attention that enforces spatial alignment across semantically matched parts, and Condition-Routed Attention which routes appearance information through geometry-conditioned pathways to maintain spatial fidelity. Coupled with a two-stage diffusion transformer, CaliTex makes geometric coherence an inherent behavior of the network rather than a byproduct of optimization. Empirically, CaliTex produces seamless and view-consistent textures and outperforms both open-source and commercial baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2511_21309
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generation
Liu, Chenyu
Chen, Hongze
Bao, Jingzhi
Zhu, Lingting
Zhang, Runze
Chen, Weikai
Hu, Zeyu
Yin, Yingda
Luo, Keyang
Wang, Xin
Computer Vision and Pattern Recognition
Despite major advances brought by diffusion-based models, current 3D texture generation systems remain hindered by cross-view inconsistency -- textures that appear convincing from one viewpoint often fail to align across others. We find that this issue arises from attention ambiguity, where unstructured full attention is applied indiscriminately across tokens and modalities, causing geometric confusion and unstable appearance-structure coupling. To address this, we introduce CaliTex, a framework of geometry-calibrated attention that explicitly aligns attention with 3D structure. It introduces two modules: Part-Aligned Attention that enforces spatial alignment across semantically matched parts, and Condition-Routed Attention which routes appearance information through geometry-conditioned pathways to maintain spatial fidelity. Coupled with a two-stage diffusion transformer, CaliTex makes geometric coherence an inherent behavior of the network rather than a byproduct of optimization. Empirically, CaliTex produces seamless and view-consistent textures and outperforms both open-source and commercial baselines.
title CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.21309