Geometry-Aware Preference Learning for 3D Texture Generation

AmirHossein Zamani, Tianhao Xie, Amir Aghdam, Tiberiu Popa, Eugene Belilovsky

Keywords: Preference Learning, Geometry-Aware 3D Texture Generation, Texture Preference Learning, Human Preference Learning

TL;DR: We propose a differentiable preference learning framework for 3D texture generation that aligns texture patterns with surface geometry using geometry-aware rewards, enabling fine-tuned, high-quality textures guided by user feedback

Abstract: Recent advances in 3D generative models have achieved impressive results but 3D contents generated by these models may not align with subjective human preferences or task-specific criteria. Moreover, a core challenge in the 3D texture generation domain remains: most existing approaches rely on repeated calls to 2D text-to-image generative models, which lack an inherent understanding of the 3D structure of the input 3D mesh object. To address this, we propose an end-to-end differentiable preference learning framework that back-propagates human preferences, represented by differentiable reward functions, through the entire 3D generative pipeline, making the process inherently geometry-aware. We demonstrate the effectiveness of our framework using four proposed novel geometry-aware reward functions, offering a more controllable and interpretable pathway for high-quality 3D content creation from natural language.

Submission Number: 25