Research map / Point clouds / Point cloud classification
Mixed Signals: A Diverse Point Cloud Dataset for Heterogeneous LiDAR V2X Collaboration
Katie Z Luo, Minh-Quan Dao, Zhenzhen Liu, Mark Campbell, Wei-Lun Chao, Kilian Q Weinberger, Ezio Malis, Vincent Fremont, Bharath Hariharan, Mao Shan, Stewart Worrall, Julie Stephany Berrio Perez
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 collaborative fusion (Attentive Fusion) over no fusion | PointPillar detector · Mixed Signals collaborative detection | Vehicle AP@IoU 0.5: 0.42 -> 0.82 | Improved |
| use Laly fusion instead of Early Fusion | collaborative detector · Mixed Signals collaborative detection | Bandwidth (MB): 7.79 -> 0.11 | Improved |
| apply detectors trained on right-hand-traffic V2V4Real to Mixed Signals (Early Fusion) | Early Fusion · Mixed Signals collaborative detection | Vehicle AP@IoU 0.5: 0.65 -> 0.24 | Hurt |
| apply V2V4Real-trained Late Fusion without retraining | Late Fusion · Mixed Signals collaborative detection | Vehicle AP@IoU 0.5: 0.43 -> 0.12 | Hurt |
| add RSU communication to Laser vehicle (Attentive Fusion) | Laser vehicle detector · Mixed Signals detection enhanced by RSU | Vehicle AP@IoU 0.5: 0.30 -> 0.71 | Improved |
| add RSU communication to EV-1 (Attentive Fusion) | EV-1 detector · Mixed Signals detection enhanced by RSU | Vehicle AP@IoU 0.5: 0.33 -> 0.53 | Improved |
| add RSU communication to EV-2 (Attentive Fusion) | EV-2 detector · Mixed Signals detection enhanced by RSU | Vehicle AP@IoU 0.5: 0.33 -> 0.56 | Improved |
| use Laser car (360-degree, intensity) instead of tilted EV LiDAR as the ego agent | Attentive Fusion with RSU · Mixed Signals detection enhanced by RSU | Vehicle AP@IoU 0.5: 0.53 -> 0.71 | Improved |
| use where2comm instead of Attentive Fusion on pedestrians | intermediate fusion · Mixed Signals collaborative detection | Pedestrian AP@IoU 0.5: 0.68 -> 0.18 | Hurt |
Closest papers by meaning
- V2X-Real: a Largs-Scale Dataset for Vehicle-to-Everything Cooperative Perception (ECCV 2024 · similarity 0.90)
- V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception (NeurIPS 2025 · similarity 0.89)
- DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detection (AAAI 2024 · similarity 0.86)
- UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception (NeurIPS 2025 · similarity 0.86)
- X-Drive: Cross-modality Consistent Multi-Sensor Data Synthesis for Driving Scenarios (ICLR 2025 · similarity 0.85)
- AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios (NeurIPS 2025 · similarity 0.85)
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.
