arXiv 2505.167612025-10-23cs.CV

Mesh-RFT：通过细粒度强化微调增强网格生成

Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning

Hong Kong University of Science and Technology（香港科技大学）；Tencent Hunyuan（腾讯文元）；University of Science and Technology of China（中国科学技术大学）；South China University of Technology（华南理工大学）

Jian Liu, Jing Xu, Song Guo, Jing Li, Jingfeng Guo, Jiaao Yu, Haohan Weng, Biwen Lei, Xianghui Yang, Zhuo Chen, Fangqi Zhu, Tao Han, Chunchao Guo

备注：: NeurIPS 2025, Spotlight

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

Mesh-RFT提出细粒度强化微调框架，利用掩码直接偏好优化和拓扑感知评分，在面级别优化网格生成，显著降低豪斯多夫距离并提升拓扑得分，实现生产级网格生成的最先进性能。

摘要：

现有的三维网格生成预训练模型常常受到数据偏差的影响，产生低质量的结果，而全局强化学习（RL）方法依赖对象级奖励，难以捕捉局部结构细节。为了解决这些挑战，我们提出了Mesh-RFT，一种新颖的细粒度强化微调框架，采用掩码直接偏好优化（M-DPO），通过质量感知的面掩码实现局部细化。为了促进高效的质量评估，我们引入了一个客观的拓扑感知评分系统，通过两个指标在对象和面级别评估几何完整性和拓扑规律性：边界边比率（BER）和拓扑得分（TS）。通过将这些指标整合到细粒度RL策略中，Mesh-RFT成为首个在单个面粒度上优化网格质量的方法，在保持全局连贯性的同时解决局部错误。实验结果表明，与预训练模型相比，我们的M-DPO方法将豪斯多夫距离（HD）降低了24.6%，并将拓扑得分（TS）提高了3.8%，同时优于全局DPO方法，HD降低17.4%，TS提升4.9%。这些结果证明了Mesh-RFT在提高几何完整性和拓扑规律性方面的能力，在面向生产的网格生成中实现了新的最先进性能。项目页面：https://hitcslj.github.io/mesh-rft/。

英文摘要：

Existing pretrained models for 3D mesh generation often suffer from data biases and produce low-quality results, while global reinforcement learning (RL) methods rely on object-level rewards that struggle to capture local structure details. To address these challenges, we present Mesh-RFT, a novel fine-grained reinforcement fine-tuning framework that employs Masked Direct Preference Optimization (M-DPO) to enable localized refinement via quality-aware face masking. To facilitate efficient quality evaluation, we introduce an objective topology-aware scoring system to evaluate geometric integrity and topological regularity at both object and face levels through two metrics: Boundary Edge Ratio (BER) and Topology Score (TS). By integrating these metrics into a fine-grained RL strategy, Mesh-RFT becomes the first method to optimize mesh quality at the granularity of individual faces, resolving localized errors while preserving global coherence. Experiment results show that our M-DPO approach reduces Hausdorff Distance (HD) by 24.6% and improves Topology Score (TS) by 3.8% over pre-trained models, while outperforming global DPO methods with a 17.4% HD reduction and 4.9% TS gain. These results demonstrate Mesh-RFT's ability to improve geometric integrity and topological regularity, achieving new state-of-the-art performance in production-ready mesh generation. Project Page: https://hitcslj.github.io/mesh-rft/.

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。