Results for TransMVSNet (Re)
Submission data
| Full name | TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers |
| Description | Reproduct TransMVSNet using the official released model. |
| Parameters | Number of depth hypotheses: 48,32,8
nviews: 7 |
| Programming language(s) | python |
| Hardware | 8 * GeForce 2080Ti |
| Submission creation date | 8 Jan, 2023 |
| Last edited | 9 Jan, 2023 |
High-res multi-view results
| Info | all | high-res multi-view | indoor | outdoor | botani. | boulde. | bridge | door | exhibi. | lectur. | living. | lounge | observ. | old co. | statue | terrac. |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 92.67 | 91.51 | 96.15 | 96.58 | 94.65 | 98.90 | 96.73 | 90.86 | 89.46 | 97.86 | 85.62 | 98.09 | 86.45 | 81.12 | 95.71 |
Low-res many-view results
| Info | all | low-res many-view | indoor | outdoor | delivery area | electro | forest | playground | terrains |
|---|---|---|---|---|---|---|---|---|---|
| No results yet. | |||||||||
Low-res two-view results
SLAM results
| all | boxes | boxes dark | buddha | cables 4 | cables 5 | desk 1 | desk 2 | desk changing 2 | desk dark 1 | desk dark 2 | desk global light changes | desk ir light | dino | drone | foreground occlusion | helmet | kidnap 2 | lamp | large loop 2 | large loop 3 | large non loop | motion 2 | motion 3 | motion 4 | planar 1 | reflective 2 | scale change | table 1 | table 2 | table 5 | table 6 | table global light changes | table local light changes | table scene | trashbin | |||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Method | Info | |||||||||||||||||||||||||||||||||||||
| No results yet. | ||||||||||||||||||||||||||||||||||||||