Research map / Multi-agent systems and games / Human-AI and goal-conditioned
VIPS: Vehicle-Infrastructure Cooperative Planning Benchmark via Pseudo-Simulation
Hoonhee Cho, Jae-young Kang, Giwon Lee, Hyemin Yang, Heejun Park, KUK-JIN YOON
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 infrastructure fusion (V2I) | CoS-V2X · VIPS detection | NDS: 17.78 -> 31.30 | Improved |
| add infrastructure fusion (V2I) | CoS-V2X · VIPS detection | mAP: 14.63 -> 28.13 | Improved |
| add infrastructure fusion (V2I) | CoS-V2X · VIPS mapping | mAP: 30.46 -> 34.24 | Improved |
| add bidirectional cross-attention only (ablation) | CoS-V2X · VIPS (S1+S2) | EPDMS: 45.80 -> 47.56 | Improved |
| add confidence-weighted fusion only (ablation) | CoS-V2X · VIPS (S1+S2) | EPDMS: 45.80 -> 48.78 | Improved |
| add both bidirectional cross-attention and confidence-weighted fusion (ablation) | CoS-V2X · VIPS (S1+S2) | EPDMS: 45.80 -> 50.88 | Improved |
| naive fusion without proposed modules vs no fusion (ablation) | CoS-V2X · VIPS (S1+S2) | EPDMS: 43.26 -> 45.80 | Improved |
| add diffusion refinement Diffix3D+ to 3DGS for vehicle view (ablation) | novel-view generation · Vehicle novel view | LPIPS: 0.414 -> 0.371 | Improved |
| replace 3DGS with masking and inpainting for infrastructure view (ablation) | novel-view generation · Infrastructure novel view | LPIPS: 0.324 -> 0.076 | Improved |
| increase transmission delay to 1000 ms (ablation) | CoS-V2X · VIPS Stage 1 | EPDMS: 78.69 -> 77.51 | Hurt |
| increase data corruption rate to 20% (ablation) | CoS-V2X · VIPS Stage 1 | EPDMS: 78.69 -> 77.00 | Hurt |
| add 8 degrees heading pose error (ablation) | CoS-V2X · VIPS Stage 1 | EPDMS: 78.69 -> 76.38 | Hurt |
Closest papers by meaning
- End-to-End Autonomous Driving Through V2X Cooperation (AAAI 2025 · similarity 0.90)
- NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking (NeurIPS 2024 · similarity 0.85)
- IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning (ICLR 2025 · similarity 0.85)
- Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving (NeurIPS 2024 · similarity 0.85)
- DriveHierarchy: A Benchmark for Diagnosing VLM Driving Capabilities from Open-Loop Understanding to Closed-Loop Execution (NeurIPS 2026 · similarity 0.85)
- URB - Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles (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.
