CAMA
CAMA copied to clipboard
Official Implementation of A Vision-Centric Approach for Static Map Element Annotation
Hi, Interesting work! I wonder when will you release map annotations for v1.0-trainval?
Hi there! Really appreciate the work :) I noticed that MapTR model trained with CAMA exhibited better performance in terms of SRE and PR scores. However, mAP on the three...
Hi, thanks for your nice work! I'm interested in the 2D segmentor that you used in CAMA. The paper mentions that you use Mask2Former to get road and lane segmentation...
When using Rome to construct a large scene, cutting the scene into small pieces would damage the entire lane or zebra crossing. How can we solve this problem