# SPLATIFY: Reproduce, Discover, Innovate! From Papers and Ideas to Trainable 3DGS Code

arXiv: https://arxiv.org/abs/2610.09116 · HTML: https://mlsanity.com/paper/2610.09116/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 69 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 23 of 23)

- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023)
- [A Survey on 3D Gaussian Splatting](https://mlsanity.com/paper/2401.03890/) (2024)
- [MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing](https://mlsanity.com/paper/2509.22186/) (2025)
- [Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning](https://mlsanity.com/paper/2504.17192/) (2025)
- [The Scene Language: Representing Scenes with Programs, Words, and Embeddings](https://mlsanity.com/paper/2410.16770/) (2024)
- [Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting](https://mlsanity.com/paper/2403.09413/) (2024)
- [AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage](https://mlsanity.com/paper/2505.20662/) (2025)
- [NerfBaselines: Consistent and Reproducible Evaluation of Novel View Synthesis Methods](https://mlsanity.com/paper/2406.17345/) (2024)
- [AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers](https://mlsanity.com/paper/2504.20115/) (2025)
- [Reflective Paper-to-Code Reproduction Enabled by Fine-Grained Verification](https://mlsanity.com/paper/2508.16671/) (2025)
- [Improving Adaptive Density Control for 3D Gaussian Splatting](https://mlsanity.com/paper/2503.14274/) (2025)
- [CLoD-GS: Continuous Level-of-Detail via 3D Gaussian Splatting](https://mlsanity.com/paper/2510.09997/) (2025)
- [BOGausS: Better Optimized Gaussian Splatting](https://mlsanity.com/paper/2504.01844/) (2025)
- [DWTGS: Rethinking Frequency Regularization for Sparse-view 3D Gaussian Splatting](https://mlsanity.com/paper/2507.15690/) (2025)
- [VoD-3DGS: View-opacity-Dependent 3D Gaussian Splatting](https://mlsanity.com/paper/2501.17978/) (2025)
- [Micro-splatting: Multistage Isotropy-informed Covariance Regularization Optimization for High-Fidelity 3D Gaussian Splatting](https://mlsanity.com/paper/2504.05740/) (2025)
- [Decomposing Densification in Gaussian Splatting for Faster 3D Scene Reconstruction](https://mlsanity.com/paper/2507.20239/) (2025)
- [NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code](https://mlsanity.com/paper/2603.00805/) (2026)
- [Trick-GS: A Balanced Bag of Tricks for Efficient Gaussian Splatting](https://mlsanity.com/paper/2501.14534/) (2025)
- [SVR-GS: Spatially Variant Regularization for Probabilistic Masks in 3D Gaussian Splatting](https://mlsanity.com/paper/2509.11116/) (2025)
- [Gradient-Driven Natural Selection for Compact 3D Gaussian Splatting](https://mlsanity.com/paper/2511.16980/) (2025)
- [Opacity-Gradient Driven Density Control for Compact and Efficient Few-Shot 3D Gaussian Splatting](https://mlsanity.com/paper/2510.10257/) (2025)
- [TIDI-GS: Floater Suppression in 3D Gaussian Splatting for Enhanced Indoor Scene Fidelity](https://mlsanity.com/paper/2601.09291/) (2026)

## Abstract (arXiv)

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.