用强化学习自动调参，提升3D高斯溅射的重建质量
RLGS: Reinforcement Learning-Based Adaptive Hyperparameter Tuning for Gaussian Splatting
- 基于强化学习构建轻量策略模块，动态调节学习率等关键参数
- 在Tanks and Temple数据集上使Taming-3DGS的PSNR提升0.7dB
- 无需修改原有架构，适用于多种主流3DGS模型
3D高斯溅射（3DGS）中的超参数调优过程繁琐且依赖专家经验，常导致重建结果不一致、性能不佳。我们提出RLGS，一种即插即用的强化学习框架，通过轻量级策略模块实现3DGS中关键超参数（如学习率、稀疏化阈值）的自适应调整。该框架与模型无关，可无缝集成至现有3DGS流程中，无需修改网络结构。我们在多个先进3DGS变体（包括Taming-3DGS和3DGS-MCMC）上验证了其泛化能力，并在不同数据集上证明其鲁棒性。在固定高斯点预算下，RLGS持续提升渲染质量，例如使Taming-3DGS在Tanks and Temple（TNT）数据集上的PSNR提升0.7dB，且在基线性能饱和时仍能带来增益。结果表明，RLGS为自动化3DGS训练超参数调优提供了一种有效且通用的解决方案，填补了强化学习在3DGS应用中的空白。
原文摘要 · Abstract (English)
Hyperparameter tuning in 3D Gaussian Splatting (3DGS) is a labor-intensive and expert-driven process, often resulting in inconsistent reconstructions and suboptimal results. We propose RLGS, a plug-and-play reinforcement learning framework for adaptive hyperparameter tuning in 3DGS through lightweight policy modules, dynamically adjusting critical hyperparameters such as learning rates and densification thresholds. The framework is model-agnostic and seamlessly integrates into existing 3DGS pipelines without architectural modifications. We demonstrate its generalization ability across multiple state-of-the-art 3DGS variants, including Taming-3DGS and 3DGS-MCMC, and validate its robustness across diverse datasets. RLGS consistently enhances rendering quality. For example, it improves Taming-3DGS by 0.7dB PSNR on the Tanks and Temple (TNT) dataset, under a fixed Gaussian budget, and continues to yield gains even when baseline performance saturates. Our results suggest that RLGS provides an effective and general solution for automating hyperparameter tuning in 3DGS training, bridging a gap in applying reinforcement learning to 3DGS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。