DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation

Benchmark Model Rank Results
monocular-depth-estimation-on-kitti-eigenDepthFormer#23absolute relative error: 0.052RMSE: 2.143Sq Rel: 0.158
monocular-depth-estimation-on-nyu-depth-v2DepthFormer#38absolute relative error: 0.096RMSE: 0.339log 10: 0.041