ST-P3

Reported on 3 benchmarks across 3 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical1 result

Semantic SegmentationonnuScenes
IoU ped - 224x480 - Vis filter. - 100x100 at 0.5· 2022-07-15
14.5
best: 19.9 (PointBeV)
ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning arXiv:2207.07601

Audio1 result

10-shot image generationonnuScenes
IoU ped - 224x480 - Vis filter. - 100x100 at 0.5· 2022-07-15
14.5
best: 19.9 (PointBeV)
ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning arXiv:2207.07601

Computer Vision1 result

Bird's-Eye View Semantic SegmentationonnuScenes
IoU ped - 224x480 - Vis filter. - 100x100 at 0.5· 2022-07-15
14.5
best: 19.9 (PointBeV)
ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning arXiv:2207.07601