EPP-MVSNet

Reported on 8 benchmarks across 3 tasks

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

Methodology6 results

3D ReconstructiononDTU
Acc
0.413
best: 0.427 (PatchmatchNet)
3D ReconstructiononDTU
Comp
0.296
best: 0.884 (3D-R2N2)
3D ReconstructiononDTU
Overall
0.355
best: 0.63 (3D-R2N2)
3DonDTU
Acc
0.413
best: 0.427 (PatchmatchNet)
3DonDTU
Comp
0.296
best: 0.884 (3D-R2N2)
3DonDTU
Overall
0.355
best: 0.63 (3D-R2N2)

Computer Vision2 results

Point CloudsonTanks and Temples
Mean F1 (Advanced)
35.72
best: 41.7 (MVSFormer++)
Point CloudsonTanks and Temples
Mean F1 (Intermediate)
61.68
best: 67.03 (MVSFormer++)