公开(公告)号：US11798197B2

公开(公告)日：2023-10-24

申请号：US17200694

申请日：2021-03-12

Applicant: QUALCOMM Incorporated

Inventor： Hoang Cong Minh Le ,  Reza Pourreza ,  Yang Yang ,  Yinhao Zhu ,  Amir Said ,  Yizhe Zhang ,  Taco Sebastiaan Cohen

IPC: G06T9/00 ,  G06N3/08 ,  G06T3/40

CPC classification number: G06T9/002 ,  G06N3/08 ,  G06T3/4046

Abstract: A method of image compression includes receiving an image. Multiple quantized latent representations are generated to represent features of the image. Each of the quantized latent representations has a different resolution and is generated at staggered timings. Each of the later generated quantized latent representations is conditioned on each of the prior generated quantized latent representations. The multiple quantized latent representations are decoded to reconstruct the image.

公开(公告)号：US20240305785A1

公开(公告)日：2024-09-12

申请号：US18457079

申请日：2023-08-28

Applicant: QUALCOMM Incorporated

Inventor： Ties Jehan Van Rozendaal ,  Hoang Cong Minh Le ,  Tushar Singhal ,  Amir Said ,  Krishna Buska ,  Guillaume Konrad Sautiere ,  Anjuman Raha ,  Auke Joris Wiggers ,  Frank Steven Mayer ,  Liang Zhang ,  Abhijit Khobare ,  Muralidhar Reddy Akula

IPC: H04N19/137 ,  H04N19/159 ,  H04N19/176 ,  H04N19/192

CPC classification number: H04N19/137 ,  H04N19/159 ,  H04N19/176 ,  H04N19/192

Abstract: An example computing device may include memory and one or more processors. The one or more processors may be configured to parallel entropy decode encoded video data from a received bitstream to generate entropy decoded data. The one or more processors may be configured to predict a motion vector based on the entropy decoded data. The one or more processors may be configured to decode a motion vector residual from the entropy decoded data. The one or more processors may be configured to add the motion vector residual and motion vector. The one or more processors may be configured to warp previous reconstructed video data with an overlapped block-based warp function using the motion vector to generate predicted current video data. The one or more processors may be configured to sum the predicted current video data with a residual block to generate current reconstructed video data.

公开(公告)号：US12177473B2

公开(公告)日：2024-12-24

申请号：US17862217

申请日：2022-07-11

Applicant: QUALCOMM Incorporated

Inventor： Reza Pourreza ,  Hoang Cong Minh Le ,  Auke Joris Wiggers

IPC: H04N19/52 ,  H04N19/105 ,  H04N19/137 ,  H04N19/172

Abstract: Systems and techniques are provided for coding video data based on an optical flow correction and a residual correction. For example, a decoding device can obtain a frame of encoded video data associated with an input frame, the frame of encoded video data including an optical flow correction and a residual correction. A predicted optical flow can be generated based on one or more reference frames and a reference optical flow. A corrected prediction frame can be generated based on the predicted optical flow and the optical flow correction. A predicted residual can be generated based on at least the corrected prediction frame and a first reference frame included in the one or more reference frames. The decoding device can generate a reconstructed input frame based on the corrected prediction frame, the predicted residual, and the residual correction.

公开(公告)号：US12132919B2

公开(公告)日：2024-10-29

申请号：US17987844

申请日：2022-11-15

Applicant: QUALCOMM Incorporated

Inventor： Yang Yang ,  Hoang Cong Minh Le ,  Yinhao Zhu ,  Reza Pourreza ,  Amir Said ,  Yizhe Zhang ,  Taco Sebastiaan Cohen

IPC: H04N19/124 ,  H04N19/119 ,  H04N19/147 ,  H04N19/17 ,  H04N19/436

CPC classification number: H04N19/436 ,  H04N19/119 ,  H04N19/124 ,  H04N19/147 ,  H04N19/17

Abstract: A processor-implemented method for image compression using an artificial neural network (ANN) includes receiving, at an encoder of the ANN, an image and a spatial segmentation map corresponding to the image. The spatial segmentation map indicates one or more regions of interest. The encoder compresses the image according to a controllable spatial bit allocation. The controllable spatial bit allocation is based on a learned quantization bin size.