Replies: 1 comment 6 replies
-
Hi @cheptil I must mention that I'm not a real researcher and have almost zero experience in ML applications to video coding. As you know, there are 2 motion estimation approaches:
Later often leads to non-trivial approaches like motion vector derivation which manages to save on rate by giving away some MV precision. So IMO you're facing a problem which requires you to do not an apple-to-apple comparison. However recently I came across couple very interesting data compression articles which may be helpful to you (that's more of a gut feeling of mine - maybe it's possible to do the optical flow MV RD optimization in latent space):
Or just read any relevant Johannes Ballé papers, they are top quality. |
Beta Was this translation helpful? Give feedback.
-
Hello, Roman
I investigate the possibility of integrate some motion estimation approach into learnable codec and have three ways:
But each of these three ways has its own disadvantages:
How do you think, which approach is most promising for rate-distortion optimization to integrate into learnable codec?
Beta Was this translation helpful? Give feedback.
All reactions