Learning-based image compression
First Claim
1. A method, comprising:
- under control of one or more computing systems comprising one or more processors,detecting a similarity between visual information in an image and information in a first set of primitive visual elements for creating images;
determining primal sketch regions in the image, the primal sketch regions including multiple associated primitive patches;
filtering the primal sketch regions to obtain primitive patches of the multiple associated primitive patches;
removing the primitive patches from the image when the primitive patches are associated with the first set of primitive visual elements;
compressing the imagereceiving the compressed image;
decompressing the compressed image; and
synthesizing the visual information that was removed, wherein the synthesizing uses a second set of primitive visual elements for creating images, wherein;
the first set of primitive visual elements is learned from first training images and the second set of primitive visual elements is learned from second training images that are different from the first training images, andlearning the first set of primitive visual elements and learning the second set of primitive visual elements use same learning strategy.
2 Assignments
0 Petitions
Accused Products
Abstract
Learning-based image compression is described. In one implementation, an encoder possessing a first set of learned visual knowledge primitives excludes visual information from an image prior to compression. A decoder possessing an independently learned set of visual knowledge primitives synthesizes the excluded visual information into the image after decompression. The encoder and decoder are decoupled with respect to the information excluded at the encoder and the information synthesized at the decoder. This results in superior data compression since the information excluded at the encoder is dropped completely and not transferred to the decoder. Primitive visual elements synthesized at the decoder may be different than primitive visual elements dropped at the encoder, but the resulting reconstituted image is perceptually equivalent to the original image.
21 Citations
13 Claims
-
1. A method, comprising:
-
under control of one or more computing systems comprising one or more processors, detecting a similarity between visual information in an image and information in a first set of primitive visual elements for creating images; determining primal sketch regions in the image, the primal sketch regions including multiple associated primitive patches; filtering the primal sketch regions to obtain primitive patches of the multiple associated primitive patches; removing the primitive patches from the image when the primitive patches are associated with the first set of primitive visual elements; compressing the image receiving the compressed image; decompressing the compressed image; and synthesizing the visual information that was removed, wherein the synthesizing uses a second set of primitive visual elements for creating images, wherein; the first set of primitive visual elements is learned from first training images and the second set of primitive visual elements is learned from second training images that are different from the first training images, and learning the first set of primitive visual elements and learning the second set of primitive visual elements use same learning strategy. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A method, comprising:
under control of one or more computing systems comprising one or more processors, learning a first set of primitive visual element pairs from a first group of training images via a learning strategy, wherein the first set is used to exclude information from an image prior to data compression; and learning a second set of primitive visual element pairs from a second group of training images via the learning strategy, wherein; the second set is used to synthesize the excluded information for reconstituting the image after data decompression, a decoder possessing the second set does not use knowledge of the primitive visual element pairs in the first set that are used to exclude image information at an encoder, and the image reconstituted via the second set is equivalent to the image from which the information was excluded via the first set. - View Dependent Claims (10, 11)
-
12. A system, comprising:
-
memory; one or processors coupled to the memory; an encoder possessing a first set of primitive visual knowledge elements for excluding information from an image prior to compression; and a decoder possessing a second set of primitive visual knowledge elements for synthesizing excluded information into the image after decompression, wherein; the decoder does not use knowledge of the primitive knowledge elements in the first set at the encoder; and the encoder does not use knowledge of the primitive visual knowledge elements in the second set at the decoder, wherein the encoder strips high-pass image information from primal sketch regions of the image prior to compression based on the first set; and wherein the decoder senses missing high-pass information at the primal sketch regions after decompression and provides the missing information from the second set. - View Dependent Claims (13)
-
Specification