Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MVSFormer++

MVSFormer++

Reported on 8 benchmarks across 3 tasks · 1 paper · 2 SOTA

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

Methodology6 results

3D ReconstructiononDTU
Acc· 2024-01-22
0.309
best: 0.427 (PatchmatchNet)
MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo arXiv:2401.11673
3D ReconstructiononDTU
Comp· 2024-01-22
0.2521
best: 0.884 (3D-R2N2)
MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo arXiv:2401.11673
3D ReconstructiononDTU
Overall· 2024-01-22
0.2805
best: 0.63 (3D-R2N2)
MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo arXiv:2401.11673
3DonDTU
Acc· 2024-01-22
0.309
best: 0.427 (PatchmatchNet)
MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo arXiv:2401.11673
3DonDTU
Comp· 2024-01-22
0.2521
best: 0.884 (3D-R2N2)
MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo arXiv:2401.11673
3DonDTU
Overall· 2024-01-22
0.2805
best: 0.63 (3D-R2N2)
MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo arXiv:2401.11673

Computer Vision2 results

Point CloudsonTanks and Temples
Mean F1 (Advanced)· 2024-01-22
41.7
SOTA
MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo arXiv:2401.11673
Point CloudsonTanks and Temples
Mean F1 (Intermediate)· 2024-01-22
67.03
SOTA
MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo arXiv:2401.11673