作者位次 #5/6SIGIR 2026Oral· Information Retrieval (Full)
Struct-Align: Zero-Shot Text-to-3D Scene Retrieval via Locality-Aware Structural Alignment
Xiong Li · Yikang Yan · Zhenyu Wen · Jie Su · Qi Chen · Zhen Hong
摘要
Text-to-3D Scene Retrieval (T3SR) aims to retrieve 3D scenes that match users' linguistic queries, enabling intuitive access to 3D scene repositories. Existing approaches rely on joint embedding learning with large amounts of paired text–scene data, which is expensive to collect and often fails t...