#artificial intelligence
Sep 2026
GoDeep: Annotation-Free Open-Vocabulary 3D Scene Understanding via Language-Space Lifting
This work uses a vision-language model purely as a translator to produce structured, entity-level descriptions of each posed image, and proposes an aggregation strategy, as a proof of concept, that favors finer elements localization in language-space embeddings.
T. Betsas, A. Doulamis, A. Georgopoulos
· arXiv.org · 0 citations