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
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 asynchronous ego-motion compensation (ACPA) with simple concatenation (ablation) | LCPS LiDAR-only baseline · NuScenes val | PQ: 72.9 -> 76.8 | Improved |
| replace simple concatenation with PVP propagation (ablation) | LCPS with ACPA · NuScenes val | PQ: 76.8 -> 77.5 | Improved |
| add semantic-aware region alignment (SARA) (ablation) | LCPS with ACPA and PVP · NuScenes val | PQ: 77.5 -> 79.2 | Improved |
| add foreground object selection gate (FOG) (ablation) | LCPS with ACPA, SARA, PVP · NuScenes val | PQ: 79.2 -> 79.8 | Improved |
| LiDAR-camera fusion over the LiDAR-only baseline on SemanticKITTI | LCPS · SemanticKITTI val | PQ: 55.7 -> 59.0 | Improved |
| fusion on a stronger SemanticKITTI baseline with heavy augmentation | LCPS · SemanticKITTI val | PQ: 60.6 -> 61.4 | Improved |
| fusion improvement on stuff classes compared with Panoptic-PHNet | LCPS · NuScenes val | PQst: 75.9 -> 75.6 | Hurt |
| perception distance 100 m instead of 50 m or unbounded volume (ablation) | LCPS LiDAR-only baseline · NuScenes val | PQ: 70.6 -> 72.9 | Improved |
| add image branch to LiDAR-only model | LCPS · SemanticKITTI inference speed | FPS (Hz): 8.6 -> 8.3 | No clear effect |
| LCPS Full versus Panoptic-PHNet on NuScenes test PQ | LCPS · NuScenes test | PQ: 80.1 -> 79.5 | Hurt |
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.
- Panoptic-PolarNet — Panoptic-PolarNet: Proposal-Free LiDAR Point Cloud Panoptic Segmentation (CVPR 2021) · better on 2 of 3 shared results
- PUPS — PUPS: Point Cloud Unified Panoptic Segmentation (AAAI 2023) · better on 1 of 2 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
- How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation (ICML 2025 · similarity 0.93)
- Exploiting the Benefits of Temporal Information in the Realm of LiDAR Panoptic Segmentation (TPAMI 2025 · similarity 0.91)
- Perception-Aware Multi-Sensor Fusion for 3D LiDAR Semantic Segmentation (ICCV 2021 · similarity 0.91)
- LiDAR-Based Panoptic Segmentation via Dynamic Shifting Network (CVPR 2021 · similarity 0.90)
- PC-BEV: An Efficient Polar-Cartesian BEV Fusion Framework for LiDAR Semantic Segmentation (AAAI 2025 · similarity 0.88)
- Multi-view Consistent 3D Panoptic Scene Understanding (AAAI 2025 · similarity 0.87)
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.
