AI Paper Atlas

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

CVPR 2026 · 3D vision › 3D generation · approach: 3D perception for autonomous driving · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add Context-Aware Association (ablation)Long-SCOPE · Griffin-25m 0-100 mAP: 0.329 -> 0.354Improved
add Context-Aware Association (ablation)Long-SCOPE · V2X-Seq 0-150 mAP: 0.352 -> 0.399Improved
add Context-Aware Association (ablation)Long-SCOPE · V2X-Seq 100-150 mAP: 0.041 -> 0.113Improved
add Context-Aware Association (ablation)Long-SCOPE · Griffin-25m 50-100 mAMOTA: 0.131 -> 0.112Hurt
add Context-Aware Association (ablation)Long-SCOPE · V2X-Seq 0-50 mAMOTA: 0.588 -> 0.576Hurt
add Geometry-guided Query Generation (ablation)Long-SCOPE · Griffin-25m 0-100 mAP: 0.284 -> 0.354Improved
add Geometry-guided Query Generation (ablation)Long-SCOPE · V2X-Seq 0-150 mAP: 0.388 -> 0.399Improved
add Geometry-guided Query Generation (ablation)Long-SCOPE · V2X-Seq 100-150 mAP: 0.113 -> 0.113No clear effect
add dynamic queries with direct depth regression to static queries (ablation)high-vantage agents · Griffin-25m 50-100 mAP: 0.092 -> 0.116Improved
derive depth from predicted global height instead of direct depth regression (ablation)dynamic queries, high-vantage agents · Griffin-25m 50-100 mAP: 0.116 -> 0.182Improved
add dynamic queries with direct depth to static queries (ablation)ground-level agents · Griffin-25m 50-100 mAP: 0.047 -> 0.052Improved
replace SparseCoop association and static queries with Long-SCOPESparseCoop · V2X-Seq 0-150 mAP: 0.334 -> 0.399Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy