AI Paper Atlas

Research map / Detection and segmentation / Tracking

3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking

Shuxiao Ding, Eike Rehder, Lukas Schneider, Marius Cordts, Juergen Gall

ICCV 2023 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 67 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
train with autoregressive sequences of length 6 instead of two-frame pairs (ablation)3DMOTFormer · nuScenes valAMOTA: 0.6741 -> 0.7121Improved
increase training length beyond T=6 (ablation)3DMOTFormer · nuScenes valAMOTA: 0.7121 -> 0.7124No clear effect
use greedy matching instead of Hungarian matching (ablation)3DMOTFormer · nuScenes valAMOTA: 0.7006 -> 0.7121Improved
use autoregressive tracks instead of GT identity guided association in training (ablation)3DMOTFormer · nuScenes valAMOTA: 0.7073 -> 0.7121Improved
pass hidden state of previous frame as initial track feature (ablation)3DMOTFormer · nuScenes valAMOTA: 0.7013 -> 0.7121Improved
add edge features to graph transformer (ablation)3DMOTFormer · nuScenes valAMOTA: 0.6469 -> 0.7121Improved
add predicted center distance in edge features (ablation)3DMOTFormer · nuScenes valAMOTA: 0.7055 -> 0.7121Improved
add frame difference to edge features (ablation)3DMOTFormer · nuScenes valAMOTA: 0.7113 -> 0.7121No clear effect
use edge-augmented graph transformer instead of node-feature affinity (cosine) (ablation)3DMOTFormer · nuScenes valAMOTA: 0.6346 -> 0.7121Improved
use sparse dynamic graph instead of fully connected graph (ablation)3DMOTFormer · nuScenes valAMOTA: 0.7015 -> 0.7121Improved
halve the graph distance threshold (ablation)3DMOTFormer · nuScenes valAMOTA: 0.7121 -> 0.6952Hurt
train on one detector and test on another3DMOTFormer · nuScenes val (target CenterPoint)AMOTA: 0.712 -> 0.699 (BEVFusion source), 0.697 (MEGVII source)Mixed

Later papers that compared with this method

2 later accepted papers report 3DMOTFormer as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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