arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2506.18331cs.CV
收藏

使用可微奖励对3D纹理生成进行端到端微调

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

Mila – Quebec AI Institute(魁北克AI研究所);Concordia University(康科迪亚大学)

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

AI总结:

本文提出了一种端到端的可微框架,通过可微奖励函数优化3D纹理生成,提升对3D结构的理解和生成质量。

摘要:

尽管最近的3D生成模型能够生成高质量的纹理图像,但它们往往无法捕捉人类的偏好或满足任务特定的要求。此外,在3D纹理生成领域,一个核心挑战是大多数现有方法依赖于多次调用2D文本到图像生成模型,这些模型缺乏对输入3D网格对象3D结构的内在理解。为缓解这些问题,我们提出了一种端到端的可微、无强化学习框架,该框架将人类反馈,以可微奖励函数的形式直接嵌入到3D纹理合成流程中。通过将偏好信号反向传播通过所提出框架的几何和外观模块,我们的方法生成的纹理尊重3D几何结构并符合期望的标准。为了证明其通用性,我们引入了三种新的几何感知奖励函数,它们为从自然语言创建高质量3D内容提供了更可控和可解释的路径。通过与最先进的方法进行定性、定量和用户偏好评估,我们证明了所提出策略在一致性上优于现有方法。我们的实现代码已公开在:https://github.com/AHHHZ975/Differentiable-Texture-Learning

英文摘要:

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. Our implementation code is publicly available at: https://github.com/AHHHZ975/Differentiable-Texture-Learning

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑