Xiong Li

Struct-Align: Zero-Shot Text-to-3D Scene Retrieval via Locality-Aware Structural Alignment

This work reformulates T3SR as a single-modality structural alignment problem by converting both 3D scenes and textual queries into a shared, schema-aligned textual representation compatible with pretrained text embedding models and introduces a role-decomposed scene structuring pipeline that mitigates generative insta...