01931a6925d3de09e5f87419d9d55055-Supplemental.pdf

In this comparison, we apply meta learning to all available networks, and show results after 10 minutes of training. The methods which use the RGB pixels produce sharp results, as the encoder and decoder do not need to be fine-tuned, but are not robust to errors in the geometry, as highlighted in the figure. These areas are inpainted in the version with a decoder.