3D 실내 장면 자동 생성 에이전트 프레임워크 제시
Scene-Designer: Learning Design Intelligence for Agentic 3D Scene Generation
- 매체
- Hugging Face
- 게시
- 중요도
- 2/5
- 화제 지수
- 14
한국어 요약
Scene-Designer는 자연어 입력에서 완성된 3D 실내 장면을 생성하는 에이전트 프레임워크다. 설계와 비평 경험을 학습하는 Scene-GRPO 방식으로 물리적 타당성, 기능적 정확성, 레이아웃 일관성을 개선한다.
원문 발췌 · English
Generating complete, coherent, and usable 3D indoor scenes from natural language requires strong design intelligence: the ability to design high-quality scenes and critique their quality. However, existing approaches either rely on general-purpose models lacking domain-specific design experience or learn from static scenes. In this work, we introduce Scene-Designer, an agentic framework that learns design intelligence through complementary design and critique experiences. We construct two datasets: Scene-OTA-35K, which provides Observation--Thought--Action supervision for learning scene design and efficient error correction, and Scene-OTC-15K, which provides Observation--Thought--Critic supervision for learning scene quality critique across physical validity, functional correctness, and layout coherence. Based on these experiences, we propose Scene-GRPO, a Critic-guided GRPO framework that improves design decisions and reduces unnecessary trial-and-error corrections. Extensive experiments demonstrate that Scene-Designer achieves superior performance in physical validity, functional correctness, and layout coherence, while the learned Scene-Critic significantly outperforms general-purpose models in scene critique. Moreover, test-time Critic guidance further improves scene generation, showing that the Critic can provide useful guidance beyond training. Additional analysis suggests a trend of mutual enhancement between scene design and critique abilities.