AI Paper Atlas

Research map / Point clouds / Segmentation and detection

CenterFormer: Center-based Transformer for 3D Object Detection

Zixiang Zhou, Xiangchen Zhao, Yu Wang, Panqu Wang, Hassan Foroosh

ECCV 2022 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 184 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 multi-scale center proposal network (ablation)center-based baseline · WOD val (single frame, mean L2 mAPH)mAPH L2: 65.9 -> 66.1No clear effect
add transformer self-attention layer (ablation)CenterFormer · WOD val (single frame, mean L2 mAPH)mAPH L2: 66.1 -> 66.8Improved
add both self- and cross-attention layers (ablation)CenterFormer · WOD val (single frame, mean L2 mAPH)mAPH L2: 66.1 -> 67.0Improved
add corner auxiliary supervision (ablation)CenterFormer · WOD val (single frame, mean L2 mAPH)mAPH L2: 67.0 -> 67.1No clear effect
add IoU rectification (ablation)CenterFormer · WOD val (single frame, mean L2 mAPH)mAPH L2: 67.1 -> 68.7Improved
add fade augmentation (ablation)CenterFormer · WOD val (single frame, mean L2 mAPH)mAPH L2: 68.7 -> 69.1Improved
replace cross-attention with deformable cross-attention (ablation)CenterFormer · WOD val (single frame, mean L2 mAPH)mAPH L2: 67.1 -> 67.3Improved
add IoU rectification to deformable model (ablation)Deformable CenterFormer · WOD val (single frame, mean L2 mAPH)mAPH L2: 67.3 -> 68.3Improved
use center feature as query instead of learnable embedding (ablation)CenterFormer · WOD valmAPH: +1.5% mAPHImproved
use center-based training instead of DETR set matching (ablation)CenterFormer · WOD valmAPH: 46.3Improved
add position embedding (ablation)CenterFormer · WOD val (20% train)mAPH L2: 59.5Improved
increase number of input frames from 1 to 8Deformable CenterFormer · WOD valmean L2 mAPH: 69.0 -> 73.7Improved

Later papers that compared with this method

7 later accepted papers report CenterFormer as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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