Login / Signup

BEVFormer: Learning Bird's-Eye-View Representation from Multi-camera Images via Spatiotemporal Transformers.

Zhiqi LiWenhai WangHongyang LiEnze XieChonghao SimaTong LuYu QiaoJifeng Dai
Published in: ECCV (9) (2022)
Keyphrases
  • camera images
  • multiple views
  • three dimensional
  • multi view
  • space time