Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion

Benchmark Model Rank Results
monocular-depth-estimation-on-kitti-eigen-splitDepthformer#33absolute relative error: 0.058RMSE: 2.285Sq Rel: 0.187…
monocular-depth-estimation-on-nyu-depth-v2Depthformer#49absolute relative error: 0.100RMSE: 0.345log 10: 0.042…