TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers

Open paper
Benchmark Model Rank Results
3d-reconstruction-on-dtuTransMVSNet#11Overall: 0.305Acc: 0.321Comp: 0.289
point-clouds-on-tanks-and-templesTransMVSNet#13Mean F1 (Advanced): 37.00Mean F1 (Intermediate): 63.52

Rank counts only results with a code link.