FuncRoom-Agent: Sequential Feed-Forward 3D Functional Indoor Scene Generation

2026-08-29

AI Summary

本文提出FuncRoom-Agent，通过递归领域特定语言、顺序前馈场景构建框架及ScenePRM过程奖励框架，解决3D功能室内场景生成的效率与功能性问题。

Abstract

We introduce Function-Room Generation, a new indoor 3D scene generation setting that creates rooms supporting explicit functional goals rather than merely visually plausible layouts. Existing agentic and executable methods improve controllability, but often depend on costly test-time generate--evaluate--revise loops, making functional room generation slow and computationally expensive. We address this challenge with three technical contributions. First, we design a recursive domain-specific language to effectively organize the hierarchical object compositions required by functional rooms, from room structure and major furniture to dense support-surface and nested small objects. It represents rooms as staged executable programs with explicit geometric and functional relations. Second, we propose a sequential feed-forward scene construction framework that distills recursive construction traces into a scene construction expert. At inference time, the expert writes executable DSL code stage by stage, and a deterministic executor directly instantiates each stage without teacher agents, online critics, or iterative repair. Third, we introduce ScenePRM, an execution-grounded process reward framework that improves the expert through reinforcement learning with functional, geometric, relational, and future-constructability feedback. We further establish a function-oriented benchmark and show state-of-the-art performance on both general indoor scene generation and function-room generation, achieving stronger functional completeness, relation correctness, geometric executability, and generation efficiency.

Problem

• 3D Indoor Scene Generation
• Functional Rooms
• Generation Efficiency
• Controllability
• Recursive Construction

Innovation

• sequential feed-forward scene construction
• recursive domain-specific language
• ScenePRM
• functional room generation