作者位次 #3/7ACL 2026Findings· Findings of ACL
S cene LM : 3 D -Aware Language Models for Editable 3 D Scene Synthesis
Xingbo Yao · Xiaoyu Chen · Doudou Zhang · Mingzhi Sheng · Boyuan Cao · Ying-Cong Chen · Hui Xiong
摘要
Synthesizing an editable 3D scene from a single RGB image is central to content creation, embodied-agent data generation, and AR/VR, yet remains challenging to achieve both high-fidelity reconstruction and convenient interactive editing. Existing geometry-based pipelines produce high-quality 3D r...