AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Perception-Aware Multi-Sensor Fusion for 3D LiDAR Semantic Segmentation

Zhuangwei Zhuang, Rong Li, Kui Jia, Qicheng Wang, Yuanqing Li, Mingkui Tan

ICCV 2021 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 231 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 perspective projection (vs spherical) with LiDAR-only input (ablation)SalsaNext · SemanticKITTI val (ablation)mIoU (%): 57.2 -> 57.6No clear effect
add perspective projection (vs spherical) with multimodal input (ablation)fusion network · SemanticKITTI val (ablation)mIoU (%): 55.8 -> 61.7Improved
add residual-based fusion modules (ablation)PMF · SemanticKITTI val (ablation)mIoU (%): 59.7 -> 61.7Improved
add perception-aware losses (ablation)PMF · SemanticKITTI val (ablation)mIoU (%): 61.7 -> 63.9Improved
use PMF instead of LiDAR-only SalsaNextPMF · SemanticKITTI val (seq 08, front-view subset)mIoU (%): 59.4 -> 63.9Improved
use PMF instead of Cylinder3DPMF · SemanticKITTI val (seq 08, front-view subset)mIoU (%): 64.9 -> 63.9Hurt
use PMF instead of Cylinder3DPMF · nuScenes valmIoU (%): 76.1 -> 76.9Improved
use PMF instead of SalsaNextPMF · nuScenes valmIoU (%): 72.2 -> 76.9Improved
use PMF instead of PointPainting fusionPMF · SemanticKITTI val (seq 08, front-view subset)mIoU (%): 54.5 -> 63.9Improved
use PMF instead of RGBAL fusionPMF · SemanticKITTI val (seq 08, front-view subset)mIoU (%): 56.2 -> 63.9Improved
use PMF instead of Cylinder3D, inference timePMF · Inference time, RTX 3090 TensorRTmIoU (%): 62.5 ms -> 22.3 msImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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