AI Paper Atlas

Research map / Point clouds / Segmentation and detection

LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment

Zhiwei Zhang, Zhizhong Zhang, Qian Yu, Ran Yi, Yuan Xie, Lizhuang Ma

ICCV 2023 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 24 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 asynchronous ego-motion compensation (ACPA) with simple concatenation (ablation)LCPS LiDAR-only baseline · NuScenes valPQ: 72.9 -> 76.8Improved
replace simple concatenation with PVP propagation (ablation)LCPS with ACPA · NuScenes valPQ: 76.8 -> 77.5Improved
add semantic-aware region alignment (SARA) (ablation)LCPS with ACPA and PVP · NuScenes valPQ: 77.5 -> 79.2Improved
add foreground object selection gate (FOG) (ablation)LCPS with ACPA, SARA, PVP · NuScenes valPQ: 79.2 -> 79.8Improved
LiDAR-camera fusion over the LiDAR-only baseline on SemanticKITTILCPS · SemanticKITTI valPQ: 55.7 -> 59.0Improved
fusion on a stronger SemanticKITTI baseline with heavy augmentationLCPS · SemanticKITTI valPQ: 60.6 -> 61.4Improved
fusion improvement on stuff classes compared with Panoptic-PHNetLCPS · NuScenes valPQst: 75.9 -> 75.6Hurt
perception distance 100 m instead of 50 m or unbounded volume (ablation)LCPS LiDAR-only baseline · NuScenes valPQ: 70.6 -> 72.9Improved
add image branch to LiDAR-only modelLCPS · SemanticKITTI inference speedFPS (Hz): 8.6 -> 8.3No clear effect
LCPS Full versus Panoptic-PHNet on NuScenes test PQLCPS · NuScenes testPQ: 80.1 -> 79.5Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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