Multi-view depth estimation on KITTI 2015 (test)
3.54Rel ErrorMASt3R
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MASt3REncoder=ViT-Large2025.03 | 3.54 | 0.6568 | |
| DUSt3R-224Resolution=224, In-domain training=false, Inference Time (s)=0.12025.03 | 4.5 | 0.55 | |
| DUNEEncoder=ViT-Base2025.03 | 4.88 | 0.5076 | |
| DUSt3R-512Resolution=512, In-domain training=false, Inference Time (s)=0.192025.03 | 5.4 | 0.495 | |
| DUSt3REncoder=ViT-Large2025.03 | 5.88 | 0.4767 | |
| MUSt3R-512Resolution=512, In-domain training=false, Inference Time (s)=0.192025.03 | 6.1 | 0.468 | |
| MUSt3R-224Resolution=224, In-domain training=false, Inference Time (s)=0.322025.03 | 7.9 | 0.362 | |
| Spann3RResolution=224, In-domain training=false, Inference Time (s)=0.292025.03 | 9.2 | 0.329 | |
| DeepV2DEncoder=Hourglass2025.03 | 10 | 0.362 |