Back to results
US 2019/0320198 A1Published application
Image encoding method and apparatus and image decoding method and apparatus
AssigneeHuawei Technologies Co., Ltd.
InventorsYin ZHAO, Peiyun DI, Lu YU
Life of this patent
Estimating the term…
Abstract
This disclosure provides an image encoding method and apparatus and an image decoding method and apparatus. For a to-be-encoded image in a to-be-encoded video sequence, a reference image may be selected from at least one knowledge-base image in a knowledge-base image set. In addition, bitstream data of the to-be-encoded image includes identification information used to identify the reference image of the to-be-encoded image.
Claims20
An image encoding method, comprising:
- obtaining a to-be-encoded image in a to-be-encoded video sequence and at least one knowledge-base image in a knowledge-base image set;
- selecting a reference image of the to-be-encoded image from the at least one knowledge-base image, wherein an image in the knowledge-base image set is used as a candidate reference image of an image in the to-be-encoded video sequence;
- and
- performing inter-frame encoding on the to-be-encoded image based on the reference image to obtain bitstream data of the to-be-encoded image, wherein the bitstream data of the to-be-encoded image comprises encoded data of the to-be-encoded image and identification information used to identify the reference image.
1 more element
An image decoding method, comprising:
- obtaining bitstream data of a to-be-decoded image, wherein the bitstream data of the to-be-decoded image comprises encoded data of the to-be-decoded image and identification information used to identify a reference image of the to-be-decoded image;
- searching, based on the identification information, a reconstructed-image set for a reconstructed image having the identification information of the reference image, wherein the reconstructed image is a knowledge-base reconstructed image obtained through reconstruction, the knowledge-base reconstructed image is a reconstructed image of an image in a knowledge-base image set, and the image in the knowledge-base image set is used as a candidate reference image of an image in a to-be-decoded video sequence in which the to-be-decoded image is located;
- and
- in response to determining that the reconstructed image having the identification information of the reference image is found, performing inter-frame decoding on the encoded data of the to-be-decoded image based on the reconstructed image having the identification information of the reference image, to obtain a reconstructed image of the to-be-decoded image.
1 more element
An image encoding apparatus, comprising:
- an obtaining unit, configured to obtain a to-be-encoded image in a to-be-encoded video sequence and at least one knowledge-base image from a knowledge-base image set;
- a selection unit, configured to select a reference image of the to-be-encoded image from the at least one knowledge-base image, wherein an image in the knowledge-base image set is used as a candidate reference image of an image in the to-be-encoded video sequence;
- and
- an encoding unit, configured to perform inter-frame encoding on the to-be-encoded image based on the reference image to obtain bitstream data of the to-be-encoded image, wherein the bitstream data of the to-be-encoded image comprises encoded data of the to-be-encoded image and identification information used to identify the reference image.
1 more element
An image decoding apparatus, comprising:
- an obtaining unit, configured to obtain bitstream data of a to-be-decoded image, wherein the bitstream data of the to-be-decoded image comprises encoded data of the to-be-decoded image and identification information used to identify a reference image of the to-be-decoded image;
- a search unit, configured to search, based on the identification information of the reference image, a reconstructed-image set for a reconstructed image having the identification information of the reference image, wherein the reconstructed image is a knowledge-base reconstructed image obtained through reconstruction, the knowledge-base reconstructed image is a reconstructed image of an image in a knowledge-base image set, and the image in the knowledge-base image set is used as a candidate reference image of an image in a to-be-decoded video sequence in which the to-be-decoded image is located;
- and
- a decoding unit, configured to:
- in response to determining that the reconstructed image having the identification information of the reference image is found, perform inter-frame decoding on the encoded data of the to-be-decoded image based on the reconstructed image having the identification information of the reference image, to obtain a reconstructed image of the to-be-decoded image.
2 more elements
Dependencies are inferred from the claim text.