AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Rethinking Range View Representation for LiDAR Segmentation

Lingdong Kong, Youquan Liu, Runnan Chen, Yuexin Ma, Xinge Zhu, Yikang Li, Yuenan Hou, Yu Qiao, Ziwei Liu

ICCV 2023 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 195 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
Cityscapes pre-training for RangeFormer (ablation)RangeFormer · SemanticKITTI val (64x2048)mIoU: 68.1 -> 69.6Improved
ImageNet pre-training for FIDNet (ablation)FIDNet · SemanticKITTI val (64x2048)mIoU: 60.4 -> 61.6Improved
ImageNet pre-training for CENet (ablation)CENet · SemanticKITTI val (64x2048)mIoU: 63.4 -> 64.1Improved
Cityscapes pre-training for RangeFormer (ablation)RangeFormer · nuScenes valmIoU: 77.1 -> 78.1Improved
train with STR multi-view partition (W_train=384) instead of W=2048CENet · SemanticKITTI testmIoU: 64.7 -> 65.8Improved
train with STR instead of W=2048FIDNet · SemanticKITTI testmIoU: 59.5 -> 60.1Improved
train RangeFormer with STR instead of W=2048RangeFormer · SemanticKITTI testmIoU: 73.3 -> 72.2Mixed
split into more than 5 views in STR (ablation)STR · SemanticKITTI valmIoUHurt
apply RangeAug augmentation instead of common augmentation (ablation)RangeFormer, CENet, FIDNet · SemanticKITTI valmIoUImproved
apply RangePost supervised sub-cloud post-processing instead of k-NN or NLA (ablation)range view segmenters · SemanticKITTI valmIoUImproved
train RangeFormer without data augmentation (plain) (ablation)RangeFormer · SemanticKITTI valmIoUHurt

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