Exploring Efficiency of Vision Transformers for Self-Supervised Monocular Depth Estimation

Benchmark Model Rank Results
monocular-depth-estimation-on-kitti-eigen-1VTDepthB2 (stereo supervision)#23absolute relative error: 0.099RMSE: 4.439RMSE log: 0.178
monocular-depth-estimation-on-kitti-eigen-1VTDepthB2 (monocular supervision)#33absolute relative error: 0.105RMSE: 4.530RMSE log: 0.182