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

arXiv: https://arxiv.org/abs/2505.16761 · HTML: https://mlsanity.com/paper/2505.16761/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 64 of its 71 references that are in the map.
- First posted on arXiv 22 May 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)
- Deep reinforcement learning methods / [RL with diffusion and flow models](https://mlsanity.com/deeprl/rl-with-diffusion-and-flow-models/)

## Builds on (most cited first, 30 of 64)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation](https://mlsanity.com/paper/2309.16653/) (2023)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://mlsanity.com/paper/2103.01458/) (2021)
- [Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation](https://mlsanity.com/paper/2303.13873/) (2023)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models](https://mlsanity.com/paper/2301.11445/) (2023)
- [CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets](https://mlsanity.com/paper/2406.13897/) (2024)
- [InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models](https://mlsanity.com/paper/2404.07191/) (2024)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [PointLLM: Empowering Large Language Models to Understand Point Clouds](https://mlsanity.com/paper/2308.16911/) (2023)
- [3D-FUTURE: 3D Furniture shape with TextURE](https://mlsanity.com/paper/2009.09633/) (2020)

## Built on by (most cited first, 22 of 22)

- [ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding](https://mlsanity.com/paper/2506.01853/) (2025)
- [Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation](https://mlsanity.com/paper/2509.12815/) (2025)
- [Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances](https://mlsanity.com/paper/2508.10316/) (2025)
- [QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Models](https://mlsanity.com/paper/2509.21420/) (2025)
- [MeshRipple: Structured Autoregressive Generation of Artist-Meshes](https://mlsanity.com/paper/2512.07514/) (2025)
- [LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents](https://mlsanity.com/paper/2603.06357/) (2026)
- [XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding](https://mlsanity.com/paper/2507.23777/) (2025)
- [FACE: A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh Generation](https://mlsanity.com/paper/2603.01515/) (2026)
- [LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow](https://mlsanity.com/paper/2607.10623/) (2026)
- [FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation](https://mlsanity.com/paper/2511.15618/) (2025)
- [Mesh-Pro: Asynchronous Advantage-guided Ranking Preference Optimization for Artist-style Quadrilateral Mesh Generation](https://mlsanity.com/paper/2603.00526/) (2026)
- [PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstruction](https://mlsanity.com/paper/2603.05888/) (2026)
- [Strips as Tokens: Artist Mesh Generation with Native UV Segmentation](https://mlsanity.com/paper/2604.09132/) (2026)
- [HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generation via Compact Autoregressive Dependence](https://mlsanity.com/paper/2601.21314/) (2026)
- [BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization](https://mlsanity.com/paper/2605.26182/) (2026)
- [MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation](https://mlsanity.com/paper/2606.04688/) (2026)
- [QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning](https://mlsanity.com/paper/2605.16813/) (2026)
- [SQuadGen: Generating Simple Quad Layouts via Chart Distance Fields](https://mlsanity.com/paper/2604.27329/) (2026)
- [Mesh-RL: Coupled subgrid reinforcement learning](https://mlsanity.com/paper/2606.26333/) (2026)
- [Sculpting NeRF Geometry: Human-Preference Fine-Tuning of a 3D-Aware Face GAN](https://mlsanity.com/paper/2606.27305/) (2026)
- [MeshOctave: Vertex Split-and-Rewire Cascades for Native Mesh Generation](https://mlsanity.com/paper/2609.38985/) (2026)
- [Q-MAGIC: Quad-only Mesh Autoregressive Generation via Singularity-Aware Circular Relative Offset Tokenization](https://mlsanity.com/paper/2610.19777/) (2026)

## Abstract (arXiv)

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/.