search

tinghuiz / SfMLearner

An unsupervised learning framework for depth and ego-motion estimation from monocular videos
MIT License
1.96k stars 555 forks source link

GT depth generation #127

Open hello7623 opened 4 years ago

hello7623 commented 4 years ago

Hello, may I ask how the GT depth image in your paper was generated?Kitti seems to have given only sparse depth maps, how to generate a pixel by pixel GT depth map

frobinet commented 4 years ago

The paper says it's interpolated from sparse measurements, so probably bilinear interpolation on top of the sparse groundtruth obtained from projecting the Lidar signal onto the camera.