GOATex: Geometry & Occlusion-Aware Texturing

2025-11-28

AI Summary

Existing 3D mesh texture generation methods struggle with occluded interior surfaces, resulting in incomplete textures and visible seams. To address this, we propose an occlusion-aware diffusion-based texture synthesis framework that requires no fine-tuning. First, multi-view ray casting constructs a hit-layer visibility structure to explicitly model visibility of both exterior and interior surfaces. Second, a two-stage visibility control strategy enables independent, text-guided synthesis for exterior and interior regions. Finally, a view-dependent confidence-weighted soft fusion mechanism is introduced in UV space to achieve high-fidelity, seam-free full-surface texturing. Our method leverages off-the-shelf pre-trained 2D diffusion models, significantly improving texture quality and geometric consistency in occluded regions while maintaining computational efficiency and enabling fine-grained appearance control. Extensive experiments demonstrate superior performance over current state-of-the-art approaches.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We present GOATex, a diffusion-based method for 3D mesh texturing that generates high-quality textures for both exterior and interior surfaces. While existing methods perform well on visible regions, they inherently lack mechanisms to handle occluded interiors, resulting in incomplete textures and visible seams. To address this, we introduce an occlusion-aware texturing framework based on the concept of hit levels, which quantify the relative depth of mesh faces via multi-view ray casting. This allows us to partition mesh faces into ordered visibility layers, from outermost to innermost. We then apply a two-stage visibility control strategy that progressively reveals interior regions with structural coherence, followed by texturing each layer using a pretrained diffusion model. To seamlessly merge textures obtained across layers, we propose a soft UV-space blending technique that weighs each texture's contribution based on view-dependent visibility confidence. Empirical results demonstrate that GOATex consistently outperforms existing methods, producing seamless, high-fidelity textures across both visible and occluded surfaces. Unlike prior works, GOATex operates entirely without costly fine-tuning of a pretrained diffusion model and allows separate prompting for exterior and interior mesh regions, enabling fine-grained control over layered appearances. For more qualitative results, please visit our project page: https://goatex3d.github.io/.

Problem

• Generates high-quality textures for both exterior and interior mesh surfaces
• Handles occluded interiors to avoid incomplete textures and visible seams
• Operates without fine-tuning diffusion models and allows separate prompting for layers

Innovation

• Uses occlusion-aware framework with hit levels for visibility layers
• Applies two-stage visibility control and diffusion model texturing
• Proposes soft UV-space blending for seamless texture merging