Skip to main content
Advertisement

< Back to Article

Human-like monocular depth biases in deep neural networks

Fig 7

Averaged affine components for human data and 31 DNNs that produce absolute depth values.

The figure comprises five subplots: scale component (az), shift component (b), horizontal shear component (ax), vertical shear component (ay), and RMSE for residual error. Error bars represent the 95% confidence intervals of the mean values, computed via bootstrap random sampling across individual data points.

Fig 7

doi: https://doi.org/10.1371/journal.pcbi.1013020.g007