We propose a method for metric-scale monocular depth estimation. Inferring depth from a single image is an ill-posed problem due to the loss of scale from perspective projection during the image formation process.

To leverage the complementary merits of both worlds, we propose BetterDepth to achieve geometrically correct affine-invariant MDE while capturing fine details.

Project page is available at https://ku-cvlab.github.io/DaRF/ .

Unsupervised monocular depth estimation techniques have demonstrated encouraging results but typically assume that the scene is static.

Table 2 shows a similar performance trend as in NYU-Depth-v2 dataset with increasing number of bins. We report results on keyframes (selected by the ORB-SLAM2) and on all frames of sequences 01-10. The A TE (m) metric is used.