Research map / 3D vision / 3D generation
Long-SCOPE: Fully Sparse Long-Range Cooperative 3D Perception
Jiahao Wang, Zikun Xu, Yuner Zhang, Zhongwei Jiang, Chenyang Lu, Shuocheng Yang, Yuxuan Wang, Jiaru Zhong, Chuang Zhang, Shaobing Xu, Jianqiang Wang
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 Context-Aware Association (ablation) | Long-SCOPE · Griffin-25m 0-100 m | AP: 0.329 -> 0.354 | Improved |
| add Context-Aware Association (ablation) | Long-SCOPE · V2X-Seq 0-150 m | AP: 0.352 -> 0.399 | Improved |
| add Context-Aware Association (ablation) | Long-SCOPE · V2X-Seq 100-150 m | AP: 0.041 -> 0.113 | Improved |
| add Context-Aware Association (ablation) | Long-SCOPE · Griffin-25m 50-100 m | AMOTA: 0.131 -> 0.112 | Hurt |
| add Context-Aware Association (ablation) | Long-SCOPE · V2X-Seq 0-50 m | AMOTA: 0.588 -> 0.576 | Hurt |
| add Geometry-guided Query Generation (ablation) | Long-SCOPE · Griffin-25m 0-100 m | AP: 0.284 -> 0.354 | Improved |
| add Geometry-guided Query Generation (ablation) | Long-SCOPE · V2X-Seq 0-150 m | AP: 0.388 -> 0.399 | Improved |
| add Geometry-guided Query Generation (ablation) | Long-SCOPE · V2X-Seq 100-150 m | AP: 0.113 -> 0.113 | No clear effect |
| add dynamic queries with direct depth regression to static queries (ablation) | high-vantage agents · Griffin-25m 50-100 m | AP: 0.092 -> 0.116 | Improved |
| derive depth from predicted global height instead of direct depth regression (ablation) | dynamic queries, high-vantage agents · Griffin-25m 50-100 m | AP: 0.116 -> 0.182 | Improved |
| add dynamic queries with direct depth to static queries (ablation) | ground-level agents · Griffin-25m 50-100 m | AP: 0.047 -> 0.052 | Improved |
| replace SparseCoop association and static queries with Long-SCOPE | SparseCoop · V2X-Seq 0-150 m | AP: 0.334 -> 0.399 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SparseCoop — SparseCoop: Cooperative Perception with Kinematic-Grounded Queries (AAAI 2026) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- SparseCoop: Cooperative Perception with Kinematic-Grounded Queries (AAAI 2026 · similarity 0.92)
- SparseAlign: a Fully Sparse Framework for Cooperative Object Detection (CVPR 2025 · similarity 0.89)
- AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios (NeurIPS 2025 · similarity 0.87)
- Far3D: Expanding the Horizon for Surround-View 3D Object Detection (AAAI 2024 · similarity 0.87)
- BEVSync: Asynchronous Data Alignment for Camera-based Vehicle-Infrastructure Cooperative Perception Under Uncertain Delays (AAAI 2025 · similarity 0.86)
- CorrBEV: Multi-View 3D Object Detection by Correlation Learning with Multi-modal Prototypes (CVPR 2025 · similarity 0.86)
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.
