公开(公告)号：US20240357112A1

公开(公告)日：2024-10-24

申请号：US18685319

申请日：2022-08-03

Applicant: Dolby Laboratories Licensing Corporation

Inventor： Arunkumar MOHANANCHETTIAR ,  Jay Nitin SHINGALA ,  Pankaj SHARMA ,  Nijil KOLLERI ,  Peng YIN ,  Arjun ARORA ,  Fangjun PU ,  Taoran LU ,  Sean Thomas MCCARTHY ,  Walter J. HUSAK

IPC: H04N19/124 ,  G06V10/771 ,  G06V10/80 ,  H04N19/46 ,  H04N19/59 ,  H04N19/70

CPC classification number: H04N19/124 ,  G06V10/771 ,  G06V10/803 ,  H04N19/46 ,  H04N19/59 ,  H04N19/70

Abstract: Methods, systems, and bitstream syntax are described for the fusion of latent features in multi-level, end-to-end, neural networks used in image and video compression. The fused architecture may be static or dynamic based on image characteristics (e.g., natural images versus screen content images) or other coding parameters, such as bitrate constrains or rate-distortion optimization. A variety of multi-level fusion architectures are discussed.

公开(公告)号：US20240422345A1

公开(公告)日：2024-12-19

申请号：US18687768

申请日：2022-08-05

Applicant: DOLBY LABORATORIES LICENSING CORPORATION

Inventor： Peng YIN ,  Fangjun PU ,  Taoran LU ,  Arjun ARORA ,  Guan-Ming SU ,  Tao CHEN ,  Sean Thomas MCCARTHY ,  Walter J. HUSAK

IPC: H04N19/517 ,  H04N19/117 ,  H04N19/82

Abstract: An input image represented in an input domain is received from an input video signal. Forward reshaping is performed on the input image to generate a forward reshaped image represented in a reshaped image domain. Non-reshaping encoding operations are performed to encode the reshaped image into an encoded video signal. At least one of the non-reshaping encoding operations is implemented with an ML model that has been previously trained with training images in one or more training datasets in a preceding training stage. A recipient device of the encoded video signal is caused to generate a reconstructed image from the forward reshaped image.