AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving

Lingdong Kong, Xiang Xu, Jiawei Ren, Wenwei Zhang, Liang Pan, Kai Chen, Wei Tsang Ooi, Ziwei Liu

TPAMI 2025 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 61 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 camera-to-LiDAR distillation and language guidance on top of LaserMixLaserMix with FIDNet · nuScenes (1% labels)mIoU: 49.5 -> 51.6Improved
add multi-modal components to LaserMixLaserMix with Cylinder3D · SemanticKITTI (1% labels)mIoU: 50.6 -> 56.2Improved
add multi-modal components to LaserMixLaserMix with SPVCNN · ScribbleKITTI (50% labels)mIoU: 61.0 -> 66.2Improved
add multi-modal components to LaserMixLaserMix with MinkUNet · nuScenes (1% labels)mIoU: 62.8 -> 64.7Improved
add multi-modal components to LaserMixLaserMix with Cylinder3D · ScribbleKITTI (10% labels)mIoU: 60.3 -> 56.7Hurt
add multi-modal components to LaserMixLaserMix with Cylinder3D · ScribbleKITTI (20% labels)mIoU: 55.1 -> 57.6Hurt
use LaserMix++ over LaserMixMinkUNet · SemanticKITTI-CmCE: 83.3 -> 80.9Improved
use LaserMix++ over LaserMixCenterPoint · WOD-CmCE: 100.5 -> 98.2Improved
use LaserMix++ over LaserMixMinkUNet · SemanticKITTI-CmRR: 87.0 -> 88.1No clear effect
add LaserMix++ as pretraining-plus-semi-supervised step instead of LaserMixSeal-pretrained backbone · nuScenes (1% labels)mIoU: 48.4 -> 49.9Improved
add LaserMix++ over LaserMixSeal-pretrained backbone · nuScenes (full labels)mIoU: 77.1 -> 77.9Improved
add LaserMix++ over LaserMixFIDNet · nuScenes (50% labels)mIoU: 73.0 -> 73.7Improved

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