hiw3c 日报精选
arXiv cs.AI/CL/LG 网页快照

反射场景:MLLM引导闭环扩散技术,用于3D室内场景生成

原文标题 · ReflectScene:MLLM-Guided Closed-Loop Diffusion for 3D Indoor Scene Generation

作者: 沈佳伟、冯杰、张俊鹏 | 文本约束式3D室内场景生成需要满足几何、功能及语义约束的布局。然而,现有扩散方法主要依赖静态文本条件,这限制了其评估动态场景以及将语义差异转化为可执行对象级修正的能力。基于MLLM的事后优化可提供语义反馈,但依然

来源:arXiv cs.AI/CL/LG · arxiv.org

正文为英文,可一键机器翻译(仅首次需要等待)

Computer Science > Computer Vision and Pattern Recognition

Title: ReflectScene:MLLM-Guided Closed-Loop Diffusion for 3D Indoor Scene Generation

Abstract: Text-conditioned 3D indoor scene generation requires layouts satisfying geometric, functional, and semantic constraints. However, existing diffusion methods rely primarily on static textual conditions, limiting their ability to assess evolving scenes and translate semantic discrepancies into executable object-level corrections. MLLM-based post-hoc refinement provides semantic feedback but remains decoupled from denoising, potentially disrupting scene this http URL propose ReflectScene, an MLLM-guided closed-loop diffusion framework. First, we introduce Hierarchical Prior-Grounded Scene Understanding that aligns structured layouts with multi-view visual evidence, to interpret object-specific context and scene global semantics via a frozen multi-modal large language model (MLLM). Second, we propose MLLM-Guided Semantic Reward Evaluation to distill MLLM's diagnoses and assessments on possible candidate corrections into a lightweight Reward Predictor, enabling correction decision making with reduced computation burden. Finally, Decision-Conditioned Trajectory-Consistent Diffusion is proposed to integrate selected corrections through transient conditioning and persistent clean-estimate projection, correcting object layout in the generated scene while preserving non-target arrangements throughout this http URL on 3D-FRONT demonstrate improved functional consistency and semantic alignment while maintaining competitive generation quality and diversity.

Submission history

Access Paper:

Additional Features

Current browse context:

References & Citations

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .