AI Paper Atlas

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

LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving

Lingdong Kong, Xiang Xu, Youquan Liu, Jun Cen, Runnan Chen, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu

TPAMI 2025 · Detection and segmentation › 3D detection and driving · approach: LiDAR perception for driving

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 VFM-based superpixels (SEEM) to camera-to-LiDAR distillation (ablation)LargeAD · nuScenes LPmIoU: 38.80 -> 43.00Improved
add superpoint temporal consistency (STC) to C2L (ablation)LargeAD · nuScenes LPmIoU: 38.80 -> 40.45Improved
add STC on top of VFM (ablation)LargeAD · nuScenes LPmIoU: 43.00 -> 44.01Improved
add point-to-segment (P2S) regularization on top of VFM (ablation)LargeAD · nuScenes LPmIoU: 43.00 -> 43.35Improved
add P2S on top of VFM and STC (ablation)LargeAD · nuScenes LPmIoU: 44.01 -> 44.95Improved
add cross-dataset pretraining (CDP) (ablation)LargeAD · nuScenes LPmIoU: 44.95 -> 46.13Improved
add cross-dataset pretraining (CDP) (ablation)LargeAD · SemanticKITTI 1%mIoU: 46.63 -> 49.55Improved
replace SLIC superpixels with SEEM (ablation)LargeAD · nuScenes LPmIoU: 40.89 -> 44.95Improved
replace SEEM with SAM superpixels (ablation)LargeAD · nuScenes LPmIoU: 44.95 -> 43.94Hurt
replace SEEM with SAM superpixels (ablation)LargeAD · nuScenes 25%mIoU: 68.41 -> 69.08Improved
use SLIC to SEEM superpixels in SLidR (ablation)SLidR · nuScenes LPmIoU: 38.80 -> 43.00Improved
use larger 2D distillation backbone (ViT-L instead of ResNet-50)LargeAD · nuScenes LPmIoU: 46.13 -> 48.71Improved

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