AI Paper Atlas

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

Rethinking the Spatio-Temporal Alignment of End-to-End 3D Perception

Xiaoyu Li, Peidong Li, Xian Wu, Long Shi, Dedong Liu, Yitao Wu, Jiajia Fu, Dixiao Cui, Lijun Zhao, Lining Sun

AAAI 2026 · Detection and segmentation › 3D detection and driving · approach: 3D objectness and scene segmentation · 1 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 HAT alignment moduleSparseDrive (2nd stage) · nuScenes valmAP / AMOTA: 41.2 -> 42.5 mAP; 36.9 -> 40.0 AMOTAImproved
add HATSparseDrive (2nd stage) · nuScenes valcollision rate (%): 0.123 -> 0.084Improved
add HATDiffusionDrive · nuScenes valcollision rate (%): 0.080 -> 0.042Improved
add HAT under snow corruptionSparseDrive · nuScenes-C snowNDS: 34.1 -> 39.1Improved
add HAT under fog corruptionSparseDrive · nuScenes-C fogmAP: 37.2 -> 37.1No clear effect
add HAT to temporal detectorsStreamPETR/Sparse4D/SimPB · nuScenes valNDS: 57.1 -> 57.8; 56.4 -> 57.3; 58.6 -> 59.0Improved
add HAT to E2E trackerADA-Track · nuScenes valAMOTA: 38.4 -> 39.7Improved
add HAT to ADA-Track on testADA-Track · nuScenes testAMOTA: 45.6 -> 46.0Improved
replace MLN with HAT as STA module (ablation)StreamPETR · nuScenes valNDS: 57.1 -> 57.8Improved
HAT vs LMM STA module (ablation)StreamPETR · nuScenes valNDS: 57.5 -> 57.8Improved
use multiple motion models vs single CV (ablation)Sparse4D · nuScenes valNDS: 56.5 -> 57.3Improved
add turning models CTRV and CTRA (ablation)Sparse4D · nuScenes valmAOE: 0.53 -> 0.42Improved

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