AI Paper Atlas

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

An End-to-End Transformer Model for 3D Object Detection

Ishan Misra, Rohit Girdhar, Armand Joulin

ICCV 2021 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 532 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
replace parametric queries with non-parametric queries (and Sine embeddings) (ablation)3DETR · ScanNetV2 valAP25: 15.4 -> 55.8Improved
replace sinusoidal with Fourier positional embeddings (ablation)3DETR · ScanNetV2 valAP25: 55.8 -> 61.8Improved
add Fourier positional embedding to the encoder (ablation)3DETR · ScanNetV2 valAP25: 62.7 -> 61.8Hurt
use set loss instead of Box loss (ablation)3DETR · ScanNetV2 valAP25: 49.6 -> 62.7Improved
use set loss instead of Vote loss (ablation)3DETR · ScanNetV2 valAP25: 54.0 -> 62.7Improved
use Transformer decoder and set loss instead of Box decoder and loss (ablation)3DETR · ScanNetV2 valAP25: 31.0 -> 62.7Improved
use Transformer decoder and set loss instead of Vote decoder and loss (ablation)3DETR · ScanNetV2 valAP25: 46.1 -> 62.7Improved
use Transformer encoder instead of PointNet++ encoder (ablation)3DETR · ScanNetV2 valAP25: 61.4 -> 62.7No clear effect
add masked self-attention encoder (3DETR-m)3DETR · ScanNetV2 valAP25: 62.7 -> 65.0Improved
add masked self-attention encoder (3DETR-m)3DETR · SUN RGB-D valAP50: 30.3 -> 32.7Mixed
add NMS at test time (ablation)VoteNet · ScanNetV2 valAP25: 10.7 -> 60.4Improved
add NMS at test time (ablation)3DETR · ScanNetV2 valAP25: 59.5 -> 62.7No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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