Research map / 3D vision / 3D generation
Rope3D: The Roadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 a ground-plane depth map to MonoDLE (ablation) | MonoDLE · Rope3D homologous (I), Car, IoU=0.5 | Rope_score: 60.36 -> 80.84 | Helped |
| Add a ground-plane depth map to MonoDLE (ablation) | MonoDLE · Rope3D heterologous (II), Car, IoU=0.5 | Rope_score: 33.72 -> 43.68 | Helped |
| Add a ground-plane depth map to MonoFlex (ablation) | MonoFlex · Rope3D homologous (I), Big Vehicle, IoU=0.5 | Rope_score: 47.96 -> 66.07 | Helped |
| Add a ground-plane depth map to MonoFlex (ablation) | MonoFlex · Rope3D heterologous (II), Car, IoU=0.5 | Rope_score: 44.37 -> 48.58 | Helped |
| Add a ground-plane depth map to M3D-RPN (ablation) | M3D-RPN · Rope3D heterologous (II), Car, IoU=0.5 | Rope_score: 36.40 -> 48.16 | Helped |
| Replace the single ground-plane equation with gridded ground planes (ablation) | KM3D · Rope3D heterologous (II), car, IoU=0.5 | AP3D|R40: 17.39 -> 23.70 | Helped |
| Replace the single ground-plane equation with gridded ground planes (ablation) | KM3D · Rope3D homologous (I), truck, IoU=0.5 | AP3D|R40: 18.42 -> 12.67 | Hurt |
| Evaluate on unseen cameras and camera specifications | MonoDLE-(G) · Rope3D Car, IoU=0.5 | Rope_score: 60.36 -> 33.72 | Hurt |
Closest papers by meaning
- BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-based Roadside 3D Object Detection (CVPR 2024 · similarity 0.88)
- RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception (CVPR 2024 · similarity 0.86)
- OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection (NeurIPS 2025 · similarity 0.86)
- TUMTraf V2X Cooperative Perception Dataset (CVPR 2024 · similarity 0.86)
- AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios (NeurIPS 2025 · similarity 0.85)
- UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception (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.