公开(公告)号：US20220138992A1

公开(公告)日：2022-05-05

申请号：US17576575

申请日：2022-01-14

Applicant: Huawei Technologies Co., Ltd. ,  University of Science and Technology of China

Inventor： Feng WU ,  Haichuan MA ,  Dong LIU ,  Haitao YANG

IPC: G06T9/00 ,  G06T3/40

Abstract: The present disclosure provides an image decoding method based on a wavelet transform. The method includes: performing entropy decoding on the compressed bitstream to obtain a reconstructed wavelet coefficient; dequantizing the reconstructed wavelet coefficient to obtain a dequantized wavelet coefficient; and performing N inverse wavelet transforms on the dequantized wavelet coefficient based on the wavelet transform model to obtain a reconstructed image, where the wavelet transform model is implemented based on a convolutional neural network (CNN).

公开(公告)号：US20190288878A1

公开(公告)日：2019-09-19

申请号：US16062486

申请日：2017-08-28

Applicant: UNIVERSITY OF SCIENCE AND TECHNOLOGY OF CHINA

Inventor： Cong SHEN ,  Fei LIANG ,  Feng WU

IPC: H04L25/02 ,  H04B1/10 ,  G06N3/04 ,  G06N3/08

Abstract: A method for decoding a signal. The method comprises decoding a received signal according to a predetermined decoding scheme and obtaining an estimate of a transmission signal based on the decoding result; obtaining an estimate of channel noise by using the correlation of channel noise; generating a modified received signal by subtracting the obtained estimate of channel noise from the received signal; and decoding the modified received signal to obtain a decoded signal according to the predetermined decoding scheme.

公开(公告)号：US20210227243A1

公开(公告)日：2021-07-22

申请号：US17221184

申请日：2021-04-02

Applicant: Huawei Technologies Co., Ltd. ,  University of Science and Technology of China

Inventor： Feng WU ,  Ning YAN ,  Dong LIU ,  Houqiang LI ,  Haitao YANG

IPC: H04N19/51 ,  H04N19/176 ,  H04N19/42 ,  H04N19/80

Abstract: Embodiments of this application disclose an interpolation filter training method and apparatus, a video picture encoding and decoding method, an encoder, and a decoder. According to the training method, a first sub-pixel picture obtained through interpolation by using a conventional interpolation filter is used as label data, to train a second interpolation filter, so that the second interpolation filter obtained through training can be directly used for a pixel value, obtained through interpolation, of a first fractional pixel position. Therefore, the label data is more accurate, and coding performance of a video picture is improved. According to the encoding method, during inter prediction, a target interpolation filter used for a current encoding picture block is determined from a set of candidate interpolation filters, and the encoder selects, according to content of the current encoding picture block, an appropriate interpolation filter to perform an interpolation operation.

公开(公告)号：US20210289214A1

公开(公告)日：2021-09-16

申请号：US17217808

申请日：2021-03-30

Applicant: Huawei Technologies Co., Ltd. ,  University of Science and Technology of China

Inventor： Feng WU ,  Fangdong CHEN ,  Houqiang LI ,  Zhuoyi LV ,  Haitao YANG

IPC: H04N19/176 ,  H04N19/46 ,  H04N19/58 ,  H04N19/179 ,  H04N19/55 ,  H04N19/573 ,  H04N19/61

Abstract: The present disclosure provides a reference image encoding method, including: encoding sequence, to obtain a reconstructed image of a first and second reference images; determining whether a local area in the second reference image is suitable for updating first reference image; determining whether the first reference image is updated; when the first reference image is not updated, and it is determined the second reference image is suitable for updating the first reference image, replacing a pixel value of a corresponding area or a related area in the first reference image with a pixel value of the local area in the second reference image; and compiling, into the bitstream.