3D Object Detection On V2Xset
평가 지표
AP0.5 (Noisy)
AP0.5 (Perfect)
AP0.7 (Noisy)
AP0.7 (Perfect)
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | AP0.5 (Noisy) | AP0.5 (Perfect) | AP0.7 (Noisy) | AP0.7 (Perfect) | Paper Title | Repository |
|---|---|---|---|---|---|---|
| V2X-ViT | 0.836 | 0.882 | 0.614 | 0.712 | V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer | |
| DiscoNet | 0.798 | 0.844 | 0.541 | 0.695 | Learning Distilled Collaboration Graph for Multi-Agent Perception | |
| AttentiveFusion | 0.709 | 0.807 | 0.487 | 0.664 | OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication | |
| F-Cooper | 0.715 | 0.840 | 0.469 | 0.680 | F-Cooper: Feature based Cooperative Perception for Autonomous Vehicle Edge Computing System Using 3D Point Clouds | |
| V2X-AHD | - | 0.855 | - | 0.724 | V2X-AHD:Vehicle-to-Everything Cooperation Perception via Asymmetric Heterogenous Distillation Network | |
| V2VNet | 0.791 | 0.845 | 0.493 | 0.677 | V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction |
0 of 6 row(s) selected.