AI Paper Atlas

Research map / 3D vision / 3D generation

Fast-BEV: A Fast and Strong Bird’s-Eye View Perception Baseline

Yangguang Li, Bin Huang, Zeren Chen, Yufeng Cui, Feng Liang, Mingzhu Shen, Fenggang Liu, Enze Xie, Lu Sheng, Wanli Ouyang, Jing Shao

TPAMI 2024 · 3D vision › 3D generation · approach: 3D perception for autonomous driving · 116 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 image augmentation (ablation)Fast-BEV 1F · nuScenes valmAP: 0.247 -> 0.285Improved
add BEV augmentation (ablation)Fast-BEV 1F · nuScenes valmAP: 0.247 -> 0.265Improved
add both image and BEV augmentation (ablation)Fast-BEV 1F · nuScenes valmAP: 0.247 -> 0.293Improved
add one history frame (2F) (ablation)Fast-BEV · nuScenes valNDS: 0.373 -> 0.451Improved
add history frames up to 4F (ablation)Fast-BEV · nuScenes valNDS: 0.451 -> 0.466Improved
add image multi-scale only (ablation)Fast-BEV 2F · nuScenes valmAP: 0.321 -> 0.320No clear effect
add BEV multi-scale only (ablation)Fast-BEV 2F · nuScenes valmAP: 0.321 -> 0.316Hurt
add image and BEV multi-scale together (ablation)Fast-BEV 2F · nuScenes valNDS: 0.451 -> 0.455Improved
increase image resolution from 256x448 to 832x1440 (ablation)Fast-BEV · nuScenes valNDS: 0.419 -> 0.491Improved
increase voxel resolution beyond 200x200x6 (ablation)Fast-BEV · nuScenes valmAP: 0.352 -> 0.337No clear effect
scale 2D encoder from R18 to R101 (ablation)Fast-BEV 4F · nuScenes valmAP: 0.293 -> 0.345Improved
scale 3D encoder from 2 to 6 blocks (ablation)Fast-BEV 4F · nuScenes valNDS: 0.446 -> 0.451Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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