Monocular Depth Estimation On Ddad
Metrics
RMSE
RMSE log
Sq Rel
absolute relative error
Results
Performance results of various models on this benchmark
Model Name | RMSE | RMSE log | Sq Rel | absolute relative error | Paper Title | Repository |
|---|---|---|---|---|---|---|
| TransDSSL | 14.350 | 0.172 | 3.591 | 0.151 | TransDSSL: Transformer based Depth Estimation via Self-Supervised Learning | |
| GEDepth | 10.596 | 0.237 | 2.119 | 0.145 | GEDepth: Ground Embedding for Monocular Depth Estimation | - |
| ScaleDepth-NK | 6.097 | - | - | 0.121 | ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation | |
| AFNet | 4.60 | 0.154 | 0.979 | 0.088 | Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving |
0 of 4 row(s) selected.