AI Paper Atlas

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

PETR: Position Embedding Transformation for Multi-View 3D Object Detection

Yingfei Liu, Tiancai Wang, Xiangyu Zhang, Jian Sun

ECCV 2022 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 776 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 3D position embedding to 2D PE (ablation)PETR · nuScenes val (ablation, ResNet-50 C5)NDS: 0.208 -> 0.356Improved
add multi-view PE to 2D PE (ablation)PETR · nuScenes val (ablation, ResNet-50 C5)NDS: 0.208 -> 0.224Improved
add 2D PE and multi-view PE on top of 3D PE (ablation)PETR · nuScenes val (ablation, ResNet-50 C5)NDS: 0.356 -> 0.359No clear effect
add MLP on 3D coordinates (ablation)PETR · nuScenes val (ablation, ResNet-50 C5)NDS: 0.311 -> 0.359Improved
use 3x3 convs instead of 1x1 in PE network (ablation)PETR · nuScenes val (ablation, ResNet-50 C5)NDS: 0.359 -> 0.017Hurt
fuse by concatenation instead of addition (ablation)PETR · nuScenes val (ablation, ResNet-50 C5)NDS: 0.359 -> 0.358No clear effect
fuse by multiplication instead of addition (ablation)PETR · nuScenes val (ablation, ResNet-50 C5)NDS: 0.359 -> 0.357Hurt
use learned 3D anchor points instead of fixed BEV anchors (ablation)PETR · nuScenes val (ablation, ResNet-50 C5)NDS: 0.337 -> 0.359Improved
use learned 3D anchor points instead of fixed 3D anchors (ablation)PETR · nuScenes val (ablation, ResNet-50 C5)NDS: 0.343 -> 0.359Improved
use anchor points instead of DETR learnable queries (ablation)PETR · nuScenes val (ablation, ResNet-50 C5)NDS: - -> 0.359Improved
increase anchor points from 600 to 1500 (ablation)PETR · nuScenes val (ablation, ResNet-50 C5)NDS: 0.339 -> 0.359Improved
linear-increasing instead of uniform depth discretization (ablation)PETR · nuScenes val (ablation, ResNet-50 C5)NDS: 0.358 -> 0.359No clear effect

Later papers that compared with this method

20 later accepted papers report PETRv2 as a baseline in their results tables; 17 of them report a better number on most of the results they share with it.

12 more not listed.

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