TPVFormer

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.

Methodology2 results

3D ReconstructiononKITTI-360
mIoU· 2023-02-15
13.64
best: 20.05 (CGFormer)
Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction arXiv:2302.07817
3DonKITTI-360
mIoU· 2023-02-15
13.64
best: 20.05 (CGFormer)
Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction arXiv:2302.07817

Computer Vision1 result

3D Semantic Scene CompletiononKITTI-360
mIoU· 2023-02-15
13.64
best: 20.05 (CGFormer)
Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction arXiv:2302.07817