AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Vision-Centric BEV Perception: A Survey

Yuexin Ma, Tai Wang, Xuyang Bai, Huitong Yang, Yuenan Hou, Yaming Wang, Yu Qiao, Ruigang Yang, Xinge Zhu

TPAMI 2024 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 228 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 fusion to BEVFormer (ablation)BEVFormer · nuScenes 3D detectionmAP / NDS / mAVE: BEVFormer-S 0.435 mAP, 0.495 NDS, 0.842 mAVE -> BEVFormer 0.481 mAP, 0.569 NDS, 0.378 mAVEImproved
add temporal fusion to PolarFormer (ablation)PolarFormer · nuScenes 3D detectionmAP / mAVE: PolarFormer-S 0.455 mAP, 0.870 mAVE -> PolarFormer 0.493 mAP, 0.440 mAVEImproved
add temporal modeling to BEVDet (BEVDet4D)BEVDet · nuScenes 3D detection (depth-based)NDS / mAVE: 0.482 -> 0.552 NDS; 0.979 -> 0.289 mAVEImproved
jointly train detection and segmentation heads on BEVFormer (ablation)BEVFormer · nuScenes detection and segmentationDrivable IoU: 80.1 -> 77.5Hurt
jointly train detection and segmentation heads on BEVFormer (ablation)BEVFormer · nuScenes detection and segmentationCar IoU: 44.8 -> 46.8Improved
jointly train detection and segmentation heads on BEVFormer (ablation)BEVFormer · nuScenes detectionNDS / mAP: 0.517 -> 0.520 NDS; 0.416 -> 0.412 mAPNo clear effect
jointly train detection and segmentation on M2BEV (ablation)M2BEV · nuScenes detection and segmentationNDS / mAP / Drivable IoU: 0.470 -> 0.454 NDS; 0.417 -> 0.408 mAP; 77.2 -> 75.9 DrivableHurt
jointly train detection and segmentation on PETRv2 (ablation)PETRv2 · nuScenes segmentationDrivable IoU / Lane IoU: 80.5 -> 79.1 Drivable; 47.4 -> 44.3 LaneHurt
jointly train detection and segmentation on Ego3RT (ablation)Ego3RT · nuScenes segmentationDrivable IoU: 79.6 -> 74.6Hurt
jointly train detection and segmentation on PolarFormer (ablation)PolarFormer · nuScenes segmentationDrivable / Lane IoU: 81.0 -> 82.6 Drivable; 42.2 -> 44.5 LaneImproved
replace MLP-based view transformation with transformer-basedPV-to-BEV methods · nuScenes BEV segmentationDrivable IoU: 70.7 -> 82.6Improved
use polar instead of Cartesian parameterizationPolarFormer · nuScenes 3D detectionmAP / NDS: BEVFormer 0.481 mAP, 0.569 NDS -> PolarFormer 0.493 mAP, 0.572 NDSImproved

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