# 3D Software Synthesis Driven by Constraint-Expressive Intermediate Representation

arXiv: https://arxiv.org/abs/2507.18625 · HTML: https://mlsanity.com/paper/2507.18625/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 93 references that are in the map.
- First posted on arXiv 24 Jul 2025.

## Builds on (most cited first, 30 of 41)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Shap-E: Generating Conditional 3D Implicit Functions](https://mlsanity.com/paper/2305.02463/) (2023)
- [3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics](https://mlsanity.com/paper/2011.09127/) (2020)
- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022)
- [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023)
- [Holodeck: Language Guided Generation of 3D Embodied AI Environments](https://mlsanity.com/paper/2312.09067/) (2023)
- [Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image](https://mlsanity.com/paper/2002.12212/) (2020)
- [DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis](https://mlsanity.com/paper/2303.14207/) (2023)
- [Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering](https://mlsanity.com/paper/2403.03163/) (2024)
- [GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks](https://mlsanity.com/paper/2311.01361/) (2023)
- [InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior](https://mlsanity.com/paper/2402.04717/) (2024)
- [GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting](https://mlsanity.com/paper/2402.07207/) (2024)
- [GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs](https://mlsanity.com/paper/2312.00093/) (2023)
- [Automated Creation of Digital Cousins for Robust Policy Learning](https://mlsanity.com/paper/2410.07408/) (2024)
- [I-Design: Personalized LLM Interior Designer](https://mlsanity.com/paper/2404.02838/) (2024)
- [AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes](https://mlsanity.com/paper/2312.06644/) (2023)
- [LEGO-Net: Learning Regular Rearrangements of Objects in Rooms](https://mlsanity.com/paper/2301.09629/) (2023)
- [DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling](https://mlsanity.com/paper/2404.03575/) (2024)
- [Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image](https://mlsanity.com/paper/1808.02201/) (2018)
- [EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion](https://mlsanity.com/paper/2405.00915/) (2024)
- [CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion](https://mlsanity.com/paper/2305.16283/) (2023)
- [Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping](https://mlsanity.com/paper/2411.03292/) (2024)
- [Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases](https://mlsanity.com/paper/2403.09675/) (2024)
- [DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation](https://mlsanity.com/paper/2506.06251/) (2025)
- [Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration](https://mlsanity.com/paper/2109.06304/) (2021)
- [WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs](https://mlsanity.com/paper/2404.06369/) (2024)
- [SceneTeller: Language-to-3D Scene Generation](https://mlsanity.com/paper/2407.20727/) (2024)
- [Indoor Scene Generation from a Collection of Semantic-Segmented Depth Images](https://mlsanity.com/paper/2108.09022/) (2021)
- [Configurable 3D Scene Synthesis and 2D Image Rendering with Per-Pixel Ground Truth using Stochastic Grammars](https://mlsanity.com/paper/1704.00112/) (2017)

## Built on by (most cited first, 4 of 4)

- [MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models](https://mlsanity.com/paper/2607.11594/) (2026)
- [Runtime Failure Hunting for Physics Engine Based Software Systems: How Far Can We Go?](https://mlsanity.com/paper/2507.22099/) (2025)
- [Frozen Scenes, Shifting Winners: Configuration Fragility in Text-to-3D Evaluation](https://mlsanity.com/paper/2610.00447/) (2026)
- [VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs](https://mlsanity.com/paper/2610.13145/) (2026)

## Abstract (arXiv)

Graphical user interface (UI) software has undergone a fundamental transformation from traditional two-dimensional (2D) desktop/web/mobile interfaces to spatial three-dimensional (3D) environments. While existing work has made remarkable success in automated 2D software generation, such as HTML/CSS and mobile app interface code synthesis, the generation of 3D software still remains under-explored. Current methods for 3D software generation usually generate the 3D environments as a whole and cannot modify or control specific elements in the software. Furthermore, these methods struggle to handle the complex spatial and semantic constraints inherent in the real world. To address the challenges, we present Scenethesis, a novel requirement-sensitive 3D software synthesis approach that maintains formal traceability between user specifications and generated 3D software. Scenethesis is built upon ScenethesisLang, a domain-specific language that serves as a granular constraint-aware intermediate representation (IR) to bridge natural language requirements and executable 3D software. It serves both as a comprehensive scene description language enabling fine-grained modification of 3D software elements and as a formal constraint-expressive specification language capable of expressing complex spatial constraints. By decomposing 3D software synthesis into stages operating on ScenethesisLang, Scenethesis enables independent verification, targeted modification, and systematic constraint satisfaction. Our evaluation demonstrates that Scenethesis accurately captures over 80% of user requirements and satisfies more than 90% of hard constraints while handling over 100 constraints simultaneously. Furthermore, Scenethesis achieves a 42.8% improvement in BLIP-2 visual evaluation scores compared to the state-of-the-art method.