摘要：3D Gaussian Splatting（3DGS）研究的快速增长，使得研究人员在进一步开展工作之前需要投入大量精力复现论文。我们提出 SPLATIFY：一个多智能体框架，可将 3DGS 论文转化为可训练的、基于 gsplat 的实现；而通用的论文转代码方法和前沿模型在这一任务上均告失败。SPLATIFY 通过五项创新实现这一目标：（1）面向 gsplat 的上下文无关文法：该文法建立在模块化方法模板之上，并为损失函数、增密、渲染和优化提供扩展点，从而约束合成过程，使生成的代码从构造上满足 gsplat 的架构不变量。（2）支持忠实复现的架构元素：包括能够在函数粒度检索组件级代码的分叉感知引用恢复机制、按拓扑依赖顺序进行的 Graph-of-Thought 合成、从超过 20 个经过验证的实现中进行 RAG 引导的上下文示例选择，以及结合 PSNR 引导再生成、高斯层面结构检查和 VLM 驱动修补的视觉反馈。（3）知识驱动的组合式改进：能够自主发现不足，并组合互补的正则化项、损失函数和增密策略，以超越原始结果。（4）跨学科方法发现：智能体从 3DGS 文献之外检索物理先验，并将其与渲染知识结合，为此前未被解决的场景类型生成方法。（5）SPLATIFY-Bench：一个覆盖 30 篇多样化 3DGS 论文的评估框架。对于没有公开代码的论文，SPLATIFY 在将开发时间从数周缩短至数分钟的同时，能够达到专家实现的水平；通过组合式发现，还可将 PSNR 最高提升 2.4 dB。我们还展示了完全由 SPLATIFY 合成的、用于体积星云渲染及其他科学领域的新方法。

Abstract:The rapid growth of 3D Gaussian Splatting (3DGS) research demands significant effort to reimplement papers before building on them. We introduce SPLATIFY, a multi-agent framework that converts 3DGS papers into trainable gsplat-based implementations, where generic paper-to-code methods and frontier models fail. SPLATIFY achieves this through five innovations: (1) A context-free grammar for gsplat over a modular method template with extension points for losses, densification, rendering, and optimization, constraining synthesis so generated code satisfies gsplat's architectural invariants by construction. (2) Architectural elements for faithful reproduction: fork-aware citation recovery retrieving component-level code at function-level granularity, Graph-of-Thought synthesis in topological dependency order, RAG-guided in-context example selection from over 20 verified implementations, and visual feedback combining PSNR-guided regeneration, Gaussian-level structural checks, and VLM-driven patching. (3) Knowledge-driven compositional improvement that autonomously finds weaknesses and composes complementary regularizers, losses, and densification strategies to improve upon original results. (4) Interdisciplinary method discovery where agents retrieve physical priors from outside the 3DGS literature and compose them with rendering knowledge to produce methods for previously unaddressed scene types. (5) SPLATIFY-Bench, an evaluation framework across 30 diverse 3DGS papers. On papers without public code, SPLATIFY matches expert implementations while reducing development time from weeks to minutes, and through compositional discovery further improves PSNR by up to 2.4 dB. We additionally demonstrate novel methods for volumetric nebula rendering and other scientific domains, synthesized entirely by SPLATIFY.