Research map / Multi-agent systems and games / Human-AI and goal-conditioned
ZeRCP: Towards Communication-Efficient Collaborative Perception and Future Scene Prediction via Request-Free Spatial Filtering
Yijie Chen, Yuzhe Ji, Haotian Wang, Xiaoyun Qiu, Ying-Cong Chen, Xinhu Zheng
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 ZeroR request-free spatial filtering to CoBEVT | CoBEVT · OPV2V BEV segmentation | mIoU: 34.2 -> 36.1 mIoU, 256.0 -> 128.0 KiB | Improved |
| use ZeroR instead of Max Pool or FMS single-phase filtering | CoBEVT · OPV2V BEV segmentation | Vehicle IoU: 47.4 -> 50.2 | Improved |
| remove all three ZeroR components (SCM, AFI, DSR) (ablation) | ZeroR · OPV2V BEV segmentation | mIoU: 33.9 -> 35.8 with all components | Improved |
| add ZeroR components, Vehicle IoU (ablation) | ZeroR · OPV2V BEV segmentation | Vehicle IoU: 43.7 -> 49.4 | Improved |
| use STDA prediction network instead of ConvLSTM/PredRNN/Fiery/ST-P3 | ZeRCP scene prediction · OPV2V scene prediction | mIoU: 27.8 -> 29.5 at 0.4s (vs ST-P3) | Improved |
| use STDA vs recurrent baselines at long horizon | ZeRCP scene prediction · OPV2V scene prediction (2.0s) | mIoU: 24.3 (ST-P3) -> 24.6 | No clear effect |
| use ZeroR instead of dual-phase SCAC/SCMF/EntropyCS | CoBEVT · OPV2V BEV segmentation | mIoU: 35.5 -> 36.1 (vs EntropyCS) | Improved |
| change STDA offset sampling counts from [4,6,8] to other configurations (ablation) | STDA · OPV2V scene prediction | mIoU: 2.0s: 24.6 vs 24.3 / 24.3 / 24.2 | No clear effect |
| use ZeroR instead of EntropyCS on Vehicle IoU | CoBEVT · OPV2V BEV segmentation | Vehicle IoU: 43.7 -> 50.2 | Improved |
Closest papers by meaning
- Generative Map Priors for Collaborative BEV Semantic Segmentation (CVPR 2025 · similarity 0.86)
- CoSDH: Communication-Efficient Collaborative Perception via Supply-Demand Awareness and Intermediate-Late Hybridization (CVPR 2025 · similarity 0.86)
- An Extensible Framework for Open Heterogeneous Collaborative Perception (ICLR 2024 · similarity 0.86)
- RCP-Bench: Benchmarking Robustness for Collaborative Perception Under Diverse Corruptions (CVPR 2025 · similarity 0.86)
- AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios (NeurIPS 2025 · similarity 0.85)
- Privacy-Preserving V2X Collaborative Perception Integrating Unknown Collaborators (AAAI 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.
