Sceniris: A Fast Procedural Scene Generation Framework

2025-12-18

AI Summary

To address the low throughput of existing procedural 3D scene generation methods—hindering large-scale dataset construction for Physical AI and embodied intelligence—this paper proposes an efficient synthetic framework. Our method introduces a novel co-design architecture integrating batched random sampling with cuRobo-accelerated GPU collision detection, enabling object-level spatial relationship modeling and diverse semantic constraints. We further propose a geometric feasibility guidance mechanism to ensure collision-free scenes and robot accessibility. Experiments demonstrate that our approach achieves ≥234× speedup over Scene Synthesizer while enabling real-time generation of highly diverse, manipulation-feasible 3D scenes. The framework supports scalable, high-fidelity scene synthesis tailored for robotics and embodied AI applications. Code is publicly available.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Intelligent Robots: Embodied AI
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Synthetic 3D scenes are essential for developing Physical AI and generative models. Existing procedural generation methods often have low output throughput, creating a significant bottleneck in scaling up dataset creation. In this work, we introduce Sceniris, a highly efficient procedural scene generation framework for rapidly generating large-scale, collision-free scene variations. Sceniris also provides an optional robot reachability check, providing manipulation-feasible scenes for robot tasks. Sceniris is designed for maximum efficiency by addressing the primary performance limitations of the prior method, Scene Synthesizer. Leveraging batch sampling and faster collision checking in cuRobo, Sceniris achieves at least 234x speed-up over Scene Synthesizer. Sceniris also expands the object-wise spatial relationships available in prior work to support diverse scene requirements. Our code is available at https://github.com/rai-inst/sceniris

Problem

• Develops a fast procedural framework for generating large-scale 3D scenes
• Addresses low throughput bottlenecks in existing scene generation methods
• Provides collision-free and manipulation-feasible scenes for Physical AI

Innovation

• Batch sampling and faster collision checking
• Optional robot reachability check for manipulation tasks
• Expands object-wise spatial relationships for diversity