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

TL;DR

CaliTex introduces geometry-calibrated attention modules within a diffusion transformer to improve 3D texture generation, ensuring view consistency and geometric coherence across multiple viewpoints.

Contribution

It proposes a novel attention mechanism that explicitly incorporates 3D geometry, addressing cross-view inconsistency in 3D texture synthesis.

Findings

Produces seamless, view-coherent textures

Outperforms existing open-source and commercial methods

Ensures geometric coherence as an inherent model behavior

Abstract

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.