Skip to main content
. Author manuscript; available in PMC: 2022 Mar 29.
Published in final edited form as: Proc IEEE Int Conf Comput Vis. 2021 Oct;2021:3376–3385. doi: 10.1109/iccv48922.2021.00338

Figure 5:

Figure 5:

Comparison between U-Net results and direct optimization (no neural network; over ΦθAB and ΦθBA) w/ and w/o added noise, using the inverse consistency loss with λ = 2,048. Direct optimization w/o noise leads to irregular maps, while adding noise or using the U-Net improves map regularity (best viewed zoomed).