AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

Center Focusing Network for Real-Time LiDAR Panoptic Segmentation

Xiaoyan Li, Gang Zhang, Boyue Wang, Yongli Hu, Baocai Yin

CVPR 2023 · Detection and segmentation › 3D detection and driving · approach: LiDAR perception for driving · 12 citations (OpenAlex)

Read the paper

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 CFFE with center feature generation to CPGNet (ablation)CFNet · SemanticKITTI validationPQ: 60.8 -> 62.7Improved
Add intermediate supervision and FEM without center feature generation (ablation)CPGNet with CDM · SemanticKITTI validationPQ: 60.5 -> 60.8Improved
Replace BEV center heatmap with CDM (ablation)PolarNet · SemanticKITTI validationPQ: 60.4 -> 60.6Improved
Replace DBSCAN, HDBSCAN, or MeanShift with CDM (ablation)CPGNet · SemanticKITTI validationPQ: +0.6~+2.2 PQImproved
Replace DBSCAN, HDBSCAN, or MeanShift with CDM (ablation)CPGNet · SemanticKITTI validationRT (ms): -21.5 ms~-81.2 msImproved
Use wider FEM receptive fields instead of setting all dilation coefficients to 1 (ablation)CFNet with CPGNet · SemanticKITTI validationPQ: 62.2 -> 62.7Improved
Use ground-truth offsets instead of predicted offsets for CFG (ablation)CFNet with CPGNet · SemanticKITTI validationPQ: 62.7 -> 65.5Improved
Use predicted CFG center offsets rather than ground-truth center offsets (ablation)CFNet with CPGNet · SemanticKITTI validationthings center offset error: 1.13 vs 1.22Hurt
Use a class-independent CDM distance threshold (ablation)CFNet · SemanticKITTI validationPQ: car: 95.2 at d=1.2; person: 85.5 at d=0.8Mixed
Use CFNet instead of Panoptic-PHNetLiDAR panoptic segmentation · SemanticKITTI testPQ: 61.5 -> 63.4Improved
Use CFNet instead of Panoptic-PHNetLiDAR panoptic segmentation · nuScenes validationPQ: 74.7 -> 75.1Improved
Use CFNet instead of Panoptic-PHNetLiDAR panoptic segmentation · nuScenes testPQ: 80.1 -> 79.4Hurt

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