You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, I am confused about the asymmetric motion field figure above, which you put in the paper. Since we only have t=0 and t=1, it is hard to judge whether the motion is symmetric or not. In my opinion, if the right foot in the above image is lower a little bit, then the motion will be symmetric and we don't have to take asymmetric motion field into account.
The text was updated successfully, but these errors were encountered:
Note that the above-attached figure is a toy example illustrating the difference between symmetric and asymmetric motion. As you mentioned, we only have t=0 and t=1. In practice, we estimate symmetric bilateral motions at such cases as a right foot.
The linear motion constraint (or symmetric fields) fails mostly when a pixel in I_t is occluded and has no matching pixel in either I_0 or I_1. Such occluded pixels belong to backgrounds in many cases. The proposed algorithm handles those pixels using asymmetric motion fields and thus improves the frame qualities in the backgrounds. The following figure demonstrates the advantage of the asymmetric motion field. The result of asymmetric motion better reconstructs the occluded facade of the building than the one of the symmetric motion.
Hi, I am confused about the asymmetric motion field figure above, which you put in the paper. Since we only have t=0 and t=1, it is hard to judge whether the motion is symmetric or not. In my opinion, if the right foot in the above image is lower a little bit, then the motion will be symmetric and we don't have to take asymmetric motion field into account.
The text was updated successfully, but these errors were encountered: