AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-Based Perception

Xinge Zhu, Hui Zhou, Tai Wang, Fangzhou Hong, Wei Li, Yuexin Ma, Hongsheng Li, Ruigang Yang, Dahua Lin

TPAMI 2021 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 138 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
replace cubic partition with cylindrical partition (ablation)3D voxel baseline · SemanticKITTI (val)mIoU: 58.1 -> 61.0Improved
add asymmetrical residual block networks (ablation)Cylinder baseline · SemanticKITTI (val)mIoU: 61.0 -> 63.8Improved
add dimension-decomposition context modeling (DDCM) (ablation)Cylinder + Asym-CNN · SemanticKITTI (val)mIoU: 63.8 -> 65.2Improved
add point-wise refinement module (ablation)Cylinder + Asym-CNN + DDCM · SemanticKITTI (val)mIoU: 65.2 -> 65.9Improved
use 1D-asymmetrical block instead of regular residual block (ablation)Cylinder3D · SemanticKITTI (val)mIoU: 60.8 -> 61.9Improved
use full asymmetrical block (with height) instead of regular block (ablation)Cylinder3D · SemanticKITTI (val)mIoU: 60.8 -> 63.9Improved
use 480x360x32 instead of 320x240x24 representation (ablation)Cylinder3D · SemanticKITTI (val)mIoU: 63.4 -> 65.9Improved
use 480x360x32 instead of 600x480x40 representation (ablation)Cylinder3D · SemanticKITTI (val)mIoU: 64.1 -> 65.9Improved
use cylindrical 480x360x32 instead of cubic 1000x1000x45 (ablation)Cylinder3D · SemanticKITTI (val)mIoU: 58.1 -> 65.9Improved
add cylindrical partition to SECOND (ablation)SECOND · nuScenes detectionNDS: 46.8 -> 49.6Improved
add asymmetrical 3D convolution to SECOND (ablation)SECOND · nuScenes detectionNDS: 46.8 -> 48.3Improved
add CyAs to SECONDSECOND · nuScenes detectionmAP: 31.6 -> 36.4Improved

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