AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

BEVFormer: Learning Bird’s-Eye-View Representation From LiDAR-Camera via Spatiotemporal Transformers

Zhiqi Li, Wenhai Wang, Hongyang Li, Enze Xie, Chonghao Sima, Tong Lü, Yu Qiao, Jifeng Dai

TPAMI 2024 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 387 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add temporal self-attention (ablation)BEVFormer-S (R101) · nuScenes valNDS: 0.448 -> 0.517Improved
add temporal self-attention (ablation)BEVFormer-S (V2-99) · nuScenes testNDS: 0.495 -> 0.569Improved
use deformable local attention instead of global attention in spatial cross-attention (ablation)BEVFormer-S · nuScenes valNDS: 0.404 -> 0.448Improved
sample local regions around reference points instead of reference points only (ablation)BEVFormer-S · nuScenes valNDS: 0.423 -> 0.448Improved
align history BEV features with ego-motion (ablation)BEVFormer · nuScenes valNDS: 0.510 -> 0.517Improved
randomly sample 4 frames from 5 during training (ablation)BEVFormer · nuScenes valNDS: 0.513 -> 0.517Improved
predict offsets and weights from both BEV queries and history BEV (ablation)BEVFormer · nuScenes valNDS: 0.513 -> 0.517Improved
increase training frames from 1 to 4 (ablation)BEVFormer · nuScenes valNDS: 0.448 -> 0.517Improved
increase training frames from 4 to 5 (ablation)BEVFormer · nuScenes valNDS: 0.517 -> 0.517No clear effect
use multi-scale view features (ablation)BEVFormer · nuScenes valNDS: 0.511 -> 0.517Improved
use 6 encoder layers instead of 1 (ablation)BEVFormer · nuScenes valNDS: 0.501 -> 0.517Improved
joint detection and segmentation training instead of segmentation onlyBEVFormer · nuScenes valLane IoU: 25.7 -> 23.9Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy