发表机构
University of California, San Diego（加利福尼亚大学圣迭戈分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SPLATIFY是一个多智能体框架，将3DGS论文自动转化为可训练的gsplat代码，通过文法约束、图思维合成和知识驱动组合，实现快速复现与性能提升，并生成新方法。
AI 中文摘要
3D高斯泼溅（3DGS）研究的快速增长要求在构建新工作之前投入大量精力重新实现论文代码。我们提出SPLATIFY，一个多智能体框架，能够将3DGS论文转化为基于gsplat的可训练实现，而通用的论文到代码方法和前沿模型在此任务上表现不佳。SPLATIFY通过五项创新实现这一目标：（1）一种针对gsplat的上下文无关文法，基于模块化方法模板，包含损失、稠密化、渲染和优化的扩展点，从而约束代码生成，使生成的代码从构造上满足gsplat的架构不变量。（2）用于忠实复现的架构要素：分支感知的引用恢复，以函数级粒度检索组件级代码；按拓扑依赖顺序进行的图思维合成；基于RAG的上下文示例选择，利用超过20个经过验证的实现；以及结合PSNR引导的再生成、高斯级结构检查和VLM驱动的补丁修复的视觉反馈。（3）知识驱动的组合式改进，自主发现弱点并组合互补的正则化器、损失和稠密化策略，以改进原始结果。（4）跨学科方法发现，智能体从3DGS文献之外检索物理先验，并将其与渲染知识组合，为先前未处理的场景类型生成方法。（5）SPLATIFY-Bench，一个涵盖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匹配专家实现，同时将开发时间从数周缩短至数分钟，并通过组合式发现进一步将PSNR提升高达2.4 dB。我们还展示了由SPLATIFY完全合成的体积星云渲染及其他科学领域的新方法。
英文摘要
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.
