AI Paper Atlas

Research map / Detection and segmentation / CNN features

Benchmarking the Robustness of LiDAR Semantic Segmentation Models

Xu Yan, Chaoda Zheng, Ying Wen Xue, Zhen Li, Shuguang Robert Cui, Dengxin Dai

IJCV 2024 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 41 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
use larger range image (2048x64 instead of 512x64) (ablation)CENet · SemanticKITTI-CmR: 70.4 -> 76.6Improved
use larger range image (2048x64 instead of 512x64) (ablation)CENet · SemanticKITTI-C local distortionmIoU: 50.5 -> 60.4Improved
use smaller range image (512x64 instead of 2048x64) for low-beam LiDAR (ablation)CENet · SemanticKITTI-C 32-beamR: 87.5 -> 90.0Improved
add attentive pooling to RandLA-Net (ablation)RandLA-Net · SemanticKITTI-CmR: 76.8 -> 80.4Improved
add attention pooling and relative-position MLP transformation to RandLA-Net (ablation)RandLA-Net · SemanticKITTI-CmR: 66.7 -> 80.4Improved
use cylindrical instead of grid voxel partition (ablation)MinkowskiNet · SemanticKITTI-C fogR: 84.9 -> 94.0Improved
use cylindrical instead of grid voxel partition (ablation)MinkowskiNet · SemanticKITTI-C snowfallR: 76.1 -> 93.0Improved
use cylindrical instead of grid voxel partition (ablation)MinkowskiNet · SemanticKITTI-C 16-beamR: 76.0 -> 50.3Hurt
use cylindrical instead of grid voxel partition (ablation)MinkowskiNet · SemanticKITTI-C cleanmIoU: 66.3 -> 63.3Hurt
increase voxel size from 5cm to 20cm (ablation)MinkowskiNet · SemanticKITTI-C global outliersR: 98.5 -> 77.7Hurt
add PointHead to 2DPASS (ablation)2DPASS · SemanticKITTI-Cclean mIoU: 65.4 -> 70.1Improved
add PointHead and point branch (hybrid) to 2DPASS (ablation)2DPASS · SemanticKITTI-CmR: 74.2 -> 72.9Hurt

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