Xindi Wu KwunFung Lau Francesco Ferroni Aljosa Osep Deva Ramanan Pix2Map: Cross-Modal Retrieval for Inferring Street Maps from Images. 17514-17523 2023 CVPR https://doi.org/10.1109/CVPR52729.2023.01680 conf/cvpr/2023 db/conf/cvpr/cvpr2023.html#WuLFOR23