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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add perspective projection (vs spherical) with LiDAR-only input (ablation) | SalsaNext · SemanticKITTI val (ablation) | mIoU (%): 57.2 -> 57.6 | No clear effect |
| add perspective projection (vs spherical) with multimodal input (ablation) | fusion network · SemanticKITTI val (ablation) | mIoU (%): 55.8 -> 61.7 | Improved |
| add residual-based fusion modules (ablation) | PMF · SemanticKITTI val (ablation) | mIoU (%): 59.7 -> 61.7 | Improved |
| add perception-aware losses (ablation) | PMF · SemanticKITTI val (ablation) | mIoU (%): 61.7 -> 63.9 | Improved |
| use PMF instead of LiDAR-only SalsaNext | PMF · SemanticKITTI val (seq 08, front-view subset) | mIoU (%): 59.4 -> 63.9 | Improved |
| use PMF instead of Cylinder3D | PMF · SemanticKITTI val (seq 08, front-view subset) | mIoU (%): 64.9 -> 63.9 | Hurt |
| use PMF instead of Cylinder3D | PMF · nuScenes val | mIoU (%): 76.1 -> 76.9 | Improved |
| use PMF instead of SalsaNext | PMF · nuScenes val | mIoU (%): 72.2 -> 76.9 | Improved |
| use PMF instead of PointPainting fusion | PMF · SemanticKITTI val (seq 08, front-view subset) | mIoU (%): 54.5 -> 63.9 | Improved |
| use PMF instead of RGBAL fusion | PMF · SemanticKITTI val (seq 08, front-view subset) | mIoU (%): 56.2 -> 63.9 | Improved |
| use PMF instead of Cylinder3D, inference time | PMF · Inference time, RTX 3090 TensorRT | mIoU (%): 62.5 ms -> 22.3 ms | Improved |
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.
- PolarNet — PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation (CVPR 2020) · better on 1 of 1 shared result
- RandLANet — RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds (CVPR 2020) · better on 1 of 1 shared result
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
- EPMF: Efficient Perception-Aware Multi-Sensor Fusion for 3D Semantic Segmentation (TPAMI 2024 · similarity 0.94)
- Exploiting the Benefits of Temporal Information in the Realm of LiDAR Panoptic Segmentation (TPAMI 2025 · similarity 0.91)
- LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment (ICCV 2023 · similarity 0.91)
- Image-to-Point Cloud Feature Back-Projection for Multimodal Training of 3D Semantic Segmentation (CVPR 2026 · similarity 0.90)
- PC-BEV: An Efficient Polar-Cartesian BEV Fusion Framework for LiDAR Semantic Segmentation (AAAI 2025 · similarity 0.89)
- Multi-Space Alignments Towards Universal LiDAR Segmentation (CVPR 2024 · similarity 0.88)
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.
