AI Paper Atlas

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

SimPB: A Single Model for 2D and 3D Object Detection from Multiple Cameras

Yingqi Tang, Zhaotie Meng, Guoliang Chen, Erkang Cheng

ECCV 2024 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 7 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 a multi-view 2D decoder layer interleaved with 3D layers (cyclic 3D-2D-3D) (ablation)SimPB hybrid decoder · nuScenes val 3D (24 epochs)NDS: 0.504 -> 0.527Improved
cyclic hybrid layers instead of cascaded 2D then 3D layers (two-stage style) (ablation)SimPB · nuScenes val 3D (24 epochs)NDS: 0.523 -> 0.527Improved
dynamic camera-parameter allocation (object center + anchor corners) instead of uniform allocation (ablation)SimPB · nuScenes val 3D (24 epochs)mAP: 0.365 -> 0.421Improved
query fusion instead of cross-attention for aggregating 2D into 3D queries (ablation)SimPB · nuScenes val 3D (24 epochs)mAP: 0.399 -> 0.421Improved
add 3D deep supervision on aggregated 3D queries (ablation)SimPB query fusion · nuScenes val 3D (24 epochs)NDS: 0.489 -> 0.527Improved
add observation angle loss (lambda 0.5) (ablation)SimPB · nuScenes val 3D (24 epochs)mAOE: 0.611 -> 0.492Improved
increase lambda_alpha from 0.5 to 1.00 (ablation)SimPB · nuScenes val 3D (24 epochs)mAP: 0.421 -> 0.418No clear effect
add one encoder layer (ablation)SimPB · nuScenes val 3D (24 epochs)mAP: 0.412 -> 0.421Improved
increase encoder layers from 1 to 4 (ablation)SimPB · nuScenes val 3D (24 epochs)mAP / FPS: mAP 0.421 -> 0.439, FPS 10.9 -> 6.1Mixed
plug SimPB hybrid decoder into DETR3DDETR3D · nuScenes val 3DNDS: 0.306 -> 0.358Improved
plug SimPB hybrid decoder into Sparse4Dv2Sparse4Dv2 · nuScenes val 3DmAP: 0.367 -> 0.398Improved
use nuImages perspective-pretrained backboneSimPB ResNet50 · nuScenes val 3DmAP: 0.475 -> 0.487Improved

Later papers that compared with this method

1 later accepted paper reports SimPB as a baseline in their results tables; 1 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 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