Paper Info

BEVFormer: Learning Bird’s-Eye-View Representation from Multi-camera Images via Spatiotemporal Transformers
Add to binder
Log in

Z Li, W Wang, H Li, E Xie, C Sima, T Lu, Y Qiao, J Dai

Lecture Notes in Computer Science, 1-18, 2022.

Reviews

From yassendobrev, rated 5/5. May 16, 2024.
A transformer-based method for depth estimation from camera data.