Jump to content

18489833. IMAGE COMPRESSION USING A VARIATIONAL AUTOENCODER (Microsoft Technology Licensing, LLC)

From WikiPatents

IMAGE COMPRESSION USING A VARIATIONAL AUTOENCODER

Organization Name

Microsoft Technology Licensing, LLC

Inventor(s)

Shudong Zhu of Issaquah WA US

IMAGE COMPRESSION USING A VARIATIONAL AUTOENCODER

This abstract first appeared for US patent application 18489833 titled 'IMAGE COMPRESSION USING A VARIATIONAL AUTOENCODER

Original Abstract Submitted

Disclosed solutions perform image compression using a variational autoencoder that enables greater compression than traditional methods, while simultaneously maintaining superior fidelity for the decompressed image. Examples persist the bottleneck layer output of a variational autoencoder as a compressed image in the form of a latent tensor. The latent tensor is decompressed by a variational autodecoder into a recovered image in pixel space. In some examples, different encoder/decoder pairs are trained on specific image types, based on feature attributes. For example, maps have lines that are narrow compared to their length (e.g., have a high aspect ratio) which are different than features within photographs of people and scenes. Some examples leverage contrastive language-image pre-training (CLIP) and/or bootstrapping language-image pre-training (BLIP) models to store embeddings, each associated with a compressed image, to enable natural language searches of compressed image collections without requiring decompression.

Cookies help us deliver our services. By using our services, you agree to our use of cookies.