NERFIFY：将NeRF论文转化为代码的多智能体框架
NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code
为NeRF论文提供自动代码复现框架，通过CFG约束LLM生成、图思维链多文件合成和视觉反馈迭代，可加速视觉研究中的可复现性验证与基线构建。
原文依据 NERFIFY achieves visual quality matching expert human code (+-0.5 dB PSNR, +-0.2 SSIM) while reducing implementation time from weeks to minutes.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论神经辐射场（NeRF）研究的激增要求在基于论文开展后续工作之前投入大量精力重新实现论文。我们提出NERFIFY，一个多智能体框架，能够可靠地将NeRF研究论文转换为可训练的Nerfstudio插件，而通用的论文到代码方法以及GPT-5等前沿模型通常无法生成可运行的代码。NERFIFY通过六项关键创新实现领域特定的可执行性：（1）上下文无关文法（CFG）：将Nerfstudio形式化为CFG来约束LLM合成，确保生成的代码满足架构不变式。（2）思维图代码合成：专门的多文件智能体按拓扑依赖顺序生成代码仓库，在每个节点验证契约和错误。（3）组合式引用恢复：智能体自动从参考文献的引用图中检索并集成组件（采样器、编码器、提议网络）。（4）视觉反馈：通过PSNR最小值ROI分析、跨视角几何验证和VLM引导的修补来诊断产物，迭代提升质量。（5）知识增强：超越复现，方法可通过新颖的正则化器或架构优化进行改进。（6）基准测试：设计了一个评估框架，用于跨30篇多样化论文的NeRF论文到代码合成。在无公开实现的论文上，NERFIFY达到与专家人工代码相当的视觉质量（±0.5 dB PSNR，±0.2 SSIM），同时将实现时间从数周缩短至数分钟。NERFIFY表明，领域感知设计能够实现复杂视觉论文的代码翻译，有望加速和 democratize 可复现研究。代码、数据和实现已公开于https://seemandhar.github.io/NERFIFY/。
英文原文摘要 1806 字符
The proliferation of neural radiance field (NeRF) research requires significant efforts to reimplement papers before building upon them. We introduce NERFIFY, a multi-agent framework that reliably converts NeRF research papers into trainable Nerfstudio plugins, in contrast to generic paper-to-code methods and frontier models like GPT-5 that usually fail to produce runnable code. NERFIFY achieves domain-specific executability through six key innovations: (1) Context-free grammar (CFG): LLM synthesis is constrained by Nerfstudio formalized as a CFG, ensuring generated code satisfies architectural invariants. (2) Graph-of-Thought code synthesis: Specialized multi-file-agents generate repositories in topological dependency order, validating contracts and errors at each node. (3) Compositional citation recovery: Agents automatically retrieve and integrate components (samplers, encoders, proposal networks) from citation graphs of references. (4) Visual feedback: Artifacts are diagnosed through PSNR-minima ROI analysis, cross-view geometric validation, and VLM-guided patching to iteratively improve quality. (5) Knowledge enhancement: Beyond reproduction, methods can be improved with novel regularizers or architectural optimizations. (6) Benchmarking: An evaluation framework is designed for NeRF paper-to-code synthesis across 30 diverse papers. On papers without public implementations, NERFIFY achieves visual quality matching expert human code (+-0.5 dB PSNR, +-0.2 SSIM) while reducing implementation time from weeks to minutes. NERFIFY demonstrates that a domain-aware design enables code translation for complex vision papers, potentiating accelerated and democratized reproducible research. Code, data and implementations are publicly available at https://seemandhar.github.io/NERFIFY/.