AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Rethinking LiDAR Domain Generalization: Single Source as Multiple Density Domains

Jaeyeul Kim, Jungwan Woo, Jeonghoon Kim, Sunghoon Im

ECCV 2024 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 9 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 point-voxel feature encoding (no intensity, voxel-wise encoding) (ablation)MinkowskiNet baseline · SemanticKITTI->nuScenesmIoU: 40.7 -> 43.0Improved
add density-aware embedding module (ablation)DDFE with point-voxel encoding · nuScenes->SemanticKITTImIoU: 35.0 -> 40.5Improved
add density soft clipping (ablation)DDFE (a)+(b) · SemanticKITTI->nuScenesmIoU: 45.7 -> 46.2Improved
add density soft clipping (ablation)DDFE (a)+(b) · nuScenes->SemanticKITTImIoU: 40.5 -> 41.8Improved
add density augmentation (enhanced-Mix3D + beam sampling) (ablation)DDFE · SemanticKITTI->nuScenesmIoU: 46.2 -> 50.1Improved
add density augmentation (ablation)DDFE · nuScenes->SemanticKITTImIoU: 41.8 -> 46.3Improved
replace Mix3D with enhanced-Mix3D (translation and rotation) (ablation)DDFE · SemanticKITTI->nuScenesmIoU: 47.4 -> 48.5Improved
add beam sampling to Mix3D (ablation)DDFE + Mix3D · nuScenes->SemanticKITTImIoU: 44.8 -> 44.2Hurt
add beam sampling to enhanced-Mix3D (ablation)DDFE + E-Mix3D · nuScenes->SemanticKITTImIoU: 46.4 -> 46.5No clear effect
use voxel size 20cm instead of 5cm (ablation)DDFE · SemanticKITTI->nuScenes (MinkNet42)mIoU: 48.6 -> 50.1 (K->N); 51.3 -> 46.3 (N->K)Mixed
apply DDFE over DGLSS on unseen domainsMinkowskiNet · Waymo->SemanticKITTImIoU: 51.23 -> 57.07Improved
add DDFE module to backboneMinkNet42 · nuScenes inference timeinference time (ms): 36ms -> 44msHurt

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