Research map / Point clouds / Segmentation and detection
Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removal
Kazuma Ikeda, Ryosei Hara, Rokuto Nagata, Ozora Sako, Zihao Ding, Takahiro Kado, Ibuki Fujioka, Taro Beppu, Mariko Isogawa, Kentaro Yoshioka
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 FWL-MAE self-supervised pretraining to the ghost detector (ablation) | FWL ghost removal baseline · Ghost-FWL test | ghost recall: 0.704 -> 0.751 | Improved |
| add FWL-MAE pretraining (ablation) | FWL ghost removal baseline · Ghost-FWL test | ghost removal rate: 0.900 -> 0.918 | Improved |
| use FWL-MAE (peak-aware) instead of MARMOT pretraining (ablation) | FWL ghost removal baseline · Ghost-FWL test | ghost recall: 0.746 -> 0.751 | Improved |
| apply ghost removal before SLAM instead of Multi-Peak | GLIM SLAM · SLAM test sequence | ATE [m]: 1.547 -> 0.245 | Improved |
| apply ghost removal before SLAM instead of Dual-Peak | GLIM SLAM · SLAM test sequence | ATE [m]: 0.715 -> 0.245 | Improved |
| apply ghost removal before 3D detection instead of Multi-Peak | PV-RCNN · Ghost-affected detection test | Ghost FP rate [%]: 67.9 -> 1.34 | Improved |
Closest papers by meaning
- GhostPoint: Self-Supervised Representation Learning by Hallucinating Occluded LiDAR Structure (ECCV 2026 · similarity 0.90)
- Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation (NeurIPS 2026 · similarity 0.88)
- LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes (CVPR 2024 · similarity 0.85)
- LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection (ICLR 2024 · similarity 0.85)
- Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion (CVPR 2024 · similarity 0.85)
- GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection (CVPR 2025 · similarity 0.84)
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.
