"TopViewRS: Vision-Language Models as Top-View Spatial Reasoners."

Chengzu Li et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2406.02537

access: open

type: Informal or Other Publication

metadata version: 2024-07-05

a service of  Schloss Dagstuhl - Leibniz Center for Informatics