End-to-End Fine-Tuning of 3D Texture Generation using Differentiable Rewards

1 Mila – Quebec AI Institute; 2 Concordia University, Montreal, Canada

IEEE/CFV Winter Conference on Applications of Computer Vision (WACV) 2026


*Corresponding Author

Abstract

While recent 3D generative models can produce high-quality texture images, they often fail to capture human preferences or meet task-specific requirements. Moreover, a core challenge in the 3D texture generation domain is that 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 alleviate these issues, we propose an end-to-end differentiable, reinforcement-learning-free framework that embeds human feedback, expressed as differentiable reward functions, directly into the 3D texture synthesis pipeline. By back-propagating preference signals through both geometric and appearance modules of the proposed framework, our method generates textures that respect the 3D geometry structure and align with desired criteria. To demonstrate its versatility, we introduce three novel geometry-aware reward functions, which offer a more controllable and interpretable pathway for creating high-quality 3D content from natural language. By conducting qualitative, quantitative, and user-preference evaluations against state-of-the-art methods, we demonstrate that our proposed strategy consistently outperforms existing approaches.

Methodology

Training overview

An overview of the proposed training process, consisting of two main stages: (i) texture generation, where a latent diffusion model generates high-quality images from textual prompts. Combined with differentiable rendering and 3D vision techniques, this step produces realistic textures for 3D objects. (ii) texture reward learning, where an end-to-end differentiable pipeline fine-tunes the pre-trained text-to-image diffusion model by maximizing a differentiable reward function r. Gradients are back-propagated through the entire 3D generative pipeline, making the process inherently geometry-aware. To demonstrate the method’s effectiveness in producing textures aligned with 3D geometry, we introduce five novel geometry-aware reward functions.

Comparative Results

Qualitative Comparison

Comparative results

Quantitative Comparison

Comparative results

More Results

BibTeX

@article{zamani2025geometry,    
  title={Geometry-Aware Preference Learning for 3D Texture Generation},
  author={Zamani, AmirHossein and Xie, Tianhao and Aghdam, Amir G and Popa, Tiberiu and Belilovsky, Eugene},
  journal={arXiv preprint arXiv:2506.18331},
  year={2025},
  url={https://ahhhz975.github.io/DifferentiableTextureLearning/}
}