Video Encoding Systems and Methods

22:

• The video encoder of claim 21, wherein the latent space residual is based on a difference between the first latent space representation and the second latent space representation.

23:

• The video encoder of claim 21, wherein the transformation of the uncompressed video content to the first latent space representation, and the transformation of the motion compensated video content to the second latent space representation, are performed in parallel.

24:

• The video encoder of claim 21, further comprising:
• a trained image compression machine learning (ML) model;
• wherein the trained image compression ML model performs transforming the uncompressed video content to the first latent space representation of the uncompressed video content, and transforming the motion compensated video content to the second latent space representation of the uncompressed video content.

25:

• The video encoder of claim 24, wherein the trained image compression ML model comprises a trained artificial neural network (NN).

26:

• The video encoder of claim 25, wherein the trained NN is trained using an objective function including an adversarial loss.

27:

• The video encoder of claim 25, wherein the trained NN comprises a generative adversarial network (GAN).

29:

• The method of claim 28, wherein the latent space residual is based on a difference between the first latent space representation and the second latent space representation.

30:

• The method of claim 28, wherein the transformation of the uncompressed video content to the first latent space representation, and the transformation of the motion compensated video content to the second latent space representation, are performed in parallel.

31:

• The method of claim 28, wherein a trained image compression machine learning (ML) model performs transforming the uncompressed video content to the first latent space representation of the uncompressed video content, and transforming the motion compensated video content to the second latent space representation of the uncompressed video content.

32:

• The method of claim 31, wherein the trained image compression ML model comprises a trained artificial neural network (NN).

33:

• The method of claim 32, wherein the trained NN is trained using an objective function including an adversarial loss.

34:

• The method of claim 32, wherein the trained NN comprises a generative adversarial network (GAN).

36:

• The computer-readable non-transitory storage medium of claim 35, wherein the latent space residual is based on a difference between the first latent space representation and the second latent space representation.

37:

• The computer-readable non-transitory storage medium of claim 35, wherein the transformation of the uncompressed video content to the first latent space representation, and the transformation of the motion compensated video content to the second latent space representation, are performed in parallel.

38:

• The computer-readable non-transitory storage medium of claim 35, wherein a trained image compression machine learning (ML) model performs transforming the uncompressed video content to the first latent space representation of the uncompressed video content, and transforming the motion compensated video content to the second latent space representation of the uncompressed video content.

39:

• The computer-readable non-transitory storage medium of claim 38, wherein the trained image compression ML model comprises a trained artificial neural network (NN).

40:

• The computer-readable non-transitory storage medium of claim 39, wherein the trained NN is trained using an objective function including an adversarial loss.