AI Paper Atlas

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

PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images

Yingfei Liu, Junjie Yan, Fan Jia, Shuailin Li, Aqi Gao, Tiancai Wang, Xiangyu Zhang

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 497 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 frame to PETR without coordinate alignment (ablation)PETR · nuScenes val (VoV-99)NDS: 0.434 -> 0.461Improved
add 3D coordinates alignment (CA) of previous frame (ablation)PETRv2 · nuScenes val (VoV-99)NDS: 0.461 -> 0.482Improved
add CA on mAVE (ablation)PETRv2 · nuScenes val (VoV-99)mAVE: 0.605 -> 0.429Improved
add feature-guided position encoder (FPE) (ablation)PETRv2 · nuScenes val (VoV-99)NDS: 0.482 -> 0.496Improved
add FPE to single-frame PETR (ablation)PETR · nuScenes val (VoV-99)NDS: 0.434 -> 0.449Improved
add FPE for robustness to extrinsics noise (ablation)PETR · nuScenes val, Rmax=8mAP drop: 6.33% -> 4.68% mAP dropImproved
add temporal multi-frame extension for robustness to extrinsics noise (ablation)PETR+FPE · nuScenes val, extrinsics noisemAP drop: 4.68% -> 4.12% mAP drop (Rmax=8)No clear effect
use 400 anchor points instead of 10 per lane (ablation)PETRv2-V · OpenLaneF-score (%): 57.8 -> 61.2Improved
stronger pretrained VoV-99 backbone instead of EfficientNetPETRv2 · OpenLaneF-score (%): 51.9 -> 57.8Improved
camera time delay of one frame interval at inferencePETRv2 · nuScenes valmAP (%): -3.19 mAP, -8.4 NDS (delay 0.083s)Hurt
drop the back camera at test timePETRv2 · nuScenes valmAP (%): -13.19% mAPHurt

Later papers that compared with this method

14 later accepted papers report PETRv2 as a baseline in their results tables; 12 of them report a better number on most of the results they share with it.

6 more not listed.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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