一句话：提出 R2SGEN 框架，以解耦 SMT 约束求解从真实世界数据合成结构化场景程序，克服组合爆炸并优于 LLM 基线。
合成训练数据的需求受 sim-to-real 鸿沟制约，现有数据驱动与基于 LLM 的生成器常产生物理上不合理的场景。为此作者提出 R2SGEN，一个从真实世界数据合成结构化场景程序的 Real-to-Sim 框架。为克服单体 SMT 编码的组合爆炸与不可解性，该工作采用解耦合成策略，把离散的结构化程序搜索与连续的几何求解分离，并以轻量原子 SMT 约束表达；同时集成两种定制剪枝机制：面向广度优先搜索的公共前缀抽象剪枝，以及面向深度优先搜索的分支限界。在 nuScenes 数据集 20 个不同复杂度的真实场景上评估，结果显示该方法保证与输入场景一致，生成程序成本显著低于 LLM 基线；两种搜索范式各有互补优势，高效且可扩展。
The demand for synthetic training data is hindered by the sim-to-real gap, as current data-driven and LLM-based generators often produce physically implausible scenarios. To address this, we propose R2SGEN, a Real-to-Sim framework that synthesizes structured scenario programs from real-world data. To overcome the combinatorial explosion and intractability of monolithic Satisfiability Modulo Theories (SMT) encoding, we introduce a decoupled synthesis strategy. This approach separates the discrete structural program search from continuous geometric resolution using lightweight, atomic SMT constraints. Furthermore, we significantly accelerate the search process by integrating two tailored pruning mechanisms: Common Prefix Abstraction-based pruning for Breadth-First Search and Branch-and-Bound for Depth-First Search. We evaluate R2SGEN on 20 real-world scenes of varying complexity from the nuScenes dataset. Experimental results show that our method guarantees consistency with the input scene and produces substantially lower-cost programs than the LLM-based baselines under the evaluated inputs. Both proposed search paradigms exhibit complementary advantages, proving highly efficient and scalable for high-complexity synthetic data generation.
@article{paperbot12117,
title = {Real-to-Sim Generation: Synthesizing Scenario Programs from Real-World Data via Constraint Solving},
author = {Peishan Huang and Wenmeng Zhang and Yusen Chen and Zhenbang Chen},
journal = {Proceedings of the ACM on Programming Languages},
volume = {10},
number = {OOPSLA2},
year = {2026},
doi = {10.1145/3839527}
}