公开(公告)号：US10681374B2

公开(公告)日：2020-06-09

申请号：US16016857

申请日：2018-06-25

Applicant: GOOGLE LLC

Inventor： Debargha Mukherjee ,  Emil Keyder ,  Michele Covell ,  Chen Wang ,  Sarah Parker ,  Ramin Zabih

IPC: H04N19/527 ,  G06T7/246 ,  H04N19/172 ,  H04N19/44 ,  H04N19/159 ,  H04N19/124 ,  H04N19/176 ,  H04N19/119 ,  H04N19/192 ,  H04N19/109 ,  H04N19/137 ,  H04N19/17 ,  H04N19/167 ,  H04N19/543 ,  H04N19/573 ,  H04N19/147 ,  H04N19/14 ,  H04N19/557

Abstract: A method for encoding a current frame of a video includes jointly determining respective motion models for reference frames and encoding the current frame using the respective motion models. The reference frames are used for encoding the current frame. Jointly determining respective motion models for reference frames includes determining respective aggregated residuals for combinations of candidate motion models and selecting the combination of candidate motion models that corresponds to the smallest aggregated residual. The respective motion models correspond to the candidate motion models of the selected combination.

公开(公告)号：US20200260112A1

公开(公告)日：2020-08-13

申请号：US16861299

申请日：2020-04-29

Applicant: GOOGLE LLC

Inventor： Debargha Mukherjee ,  Emil Keyder ,  Michele Covell ,  Chen Wang ,  Sarah Parker ,  Ramin Zabih

IPC: H04N19/527 ,  H04N19/147 ,  H04N19/573 ,  H04N19/543 ,  H04N19/167 ,  H04N19/17 ,  H04N19/137 ,  H04N19/109 ,  H04N19/192 ,  H04N19/119 ,  H04N19/176 ,  H04N19/124 ,  H04N19/159 ,  H04N19/44 ,  H04N19/172 ,  G06T7/246

Abstract: An apparatus for encoding a current frame of a video. The apparatus includes a memory and a processor. The processor is configured to execute instructions stored in the memory to generate, for each reference frame of a subset of available reference frames, at least one respective candidate global motion model (GMM); partition the current frame into blocks; generate an aggregated residual frame for the current frame; and encode the respective residual blocks in a compressed bitstream. To generate the aggregated residual frame includes to select, for predicting each block of the blocks, a respective selected GMM, where the respective selected GMM corresponds to the one of the at least one respective candidate GMMs that minimizes a total error associated with the aggregated residual frame; and obtain respective residual blocks for the block.

公开(公告)号：US11115678B2

公开(公告)日：2021-09-07

申请号：US16861299

申请日：2020-04-29

Applicant: GOOGLE LLC

Inventor： Debargha Mukherjee ,  Emil Keyder ,  Michele Covell ,  Chen Wang ,  Sarah Parker ,  Ramin Zabih

IPC: H04N19/527 ,  H04N19/172 ,  H04N19/176 ,  H04N19/109 ,  G06T7/246 ,  H04N19/44 ,  H04N19/159 ,  H04N19/124 ,  H04N19/119 ,  H04N19/192 ,  H04N19/137 ,  H04N19/17 ,  H04N19/167 ,  H04N19/543 ,  H04N19/573 ,  H04N19/147 ,  H04N19/14 ,  H04N19/557

Abstract: An apparatus for encoding a current frame of a video. The apparatus includes a memory and a processor. The processor is configured to execute instructions stored in the memory to generate, for each reference frame of a subset of available reference frames, at least one respective candidate global motion model (GMM); partition the current frame into blocks; generate an aggregated residual frame for the current frame; and encode the respective residual blocks in a compressed bitstream. To generate the aggregated residual frame includes to select, for predicting each block of the blocks, a respective selected GMM, where the respective selected GMM corresponds to the one of the at least one respective candidate GMMs that minimizes a total error associated with the aggregated residual frame; and obtain respective residual blocks for the block.

公开(公告)号：US20190149841A1

公开(公告)日：2019-05-16

申请号：US16016857

申请日：2018-06-25

Applicant: GOOGLE LLC

Inventor： Debargha Mukherjee ,  Emil Keyder ,  Michele Covell ,  Chen Wang ,  Sarah Parker ,  Ramin Zabih

IPC: H04N19/527 ,  G06T7/246 ,  H04N19/172 ,  H04N19/176 ,  H04N19/159 ,  H04N19/124 ,  H04N19/44

Abstract: A method for encoding a current frame of a video includes jointly determining respective motion models for reference frames and encoding the current frame using the respective motion models. The reference frames are used for encoding the current frame. Jointly determining respective motion models for reference frames includes determining respective aggregated residuals for combinations of candidate motion models and selecting the combination of candidate motion models that corresponds to the smallest aggregated residual. The respective motion models correspond to the candidate motion models of the selected combination.