# US 12,015,785 B2 · No reference image quality assessment based decoder side inter prediction > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,015,785 B2 - Document ID: US12015785B2 - Status: Granted - Kind: B2 - Application number: 17/543,214 - Filed: 2021-12-06 - Published: 2022-06-09 - Granted: 2024-06-18 - Earliest claimed: 2020-12-04 - Assignees: Ofinno, LLC - Applicants: Ofinno, LLC - Inventors: Tae Meon Bae; Esmael Hejazi Dinan; Kalyan Goswami - Web page: https://patentgrep.com/patent/US12015785B2 ## CPC - H04N 19/154: Measured or subjectively estimated visual quality after decoding, e.g. measurement of distortion (use of rate-distortion criteria H04N19/147) - H04N 19/109: among a plurality of temporal predictive coding modes - H04N 19/124: Quantisation - H04N 19/137: Motion inside a coding unit, e.g. average field, frame or block difference - H04N 19/147: according to rate distortion criteria (rate-distortion as a criterion for motion estimation H04N19/567) - H04N 19/176: the region being a block, e.g. a macroblock - H04N 19/18: the unit being a set of transform coefficients - H04N 19/52: by predictive encoding - H04N 19/567: Motion estimation based on rate distortion criteria - H04N 19/70: characterised by syntax aspects related to video coding, e.g. related to compression standards - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract A decoder may determine first motion information, from of a plurality of motion information, for a block. The decoder may generate, for each respective motion information of the plurality of motion information, a reconstructed block. The decoder may generate the reconstructed block, for each respective motion information of the plurality of motion information, based on: a prediction block generated for the respective motion information; and a reconstructed residual block based on the first motion information. The decoder may determine second motion information, from the plurality of motion information, for the block based on a visual quality of each of the reconstructed blocks. The decoder may signal, based on the second motion information, the first motion information in a bit stream. ## Claims ### Claim 1 A method comprising: determining first motion information, from a plurality of motion information, for encoding a block; determining a residual block based on a difference between the block and a first prediction block that is based on the first motion information; for each respective motion information of the plurality of motion information: generating a reconstructed block based on: a prediction block generated using the respective motion information; and a reconstruction of the residual block determined based on the first motion information; and determining a visual quality of the reconstructed block without using the block as a reference; and determining, based on the visual qualities of the reconstructed blocks, second motion information, from the plurality of motion information, as a prediction of the first motion information determined for the block; and signaling, in a bitstream, an indication indicating whether the first motion information is the same as the second motion information. ### Claim 2 (depends on 1) The method of claim 1, wherein the first motion information comprises a motion vector and a reference picture number. ### Claim 3 (depends on 1) The method of claim 1, wherein the determining the second motion information further comprises determining the second motion information for the block based on the visual quality, among the visual qualities of the reconstructed blocks, with a highest visual quality. ### Claim 4 (depends on 1) The method of claim 1, wherein the visual quality of the reconstructed block is determined based on a visual parameter measurement index or a deep Learning for Blind Image Quality Assessment. ### Claim 5 (depends on 1) The method of claim 1, wherein the generating the reconstructed block comprises summing: the reconstructed residual block; and the prediction block based on the respective motion information. ### Claim 6 (depends on 5) The method of claim 5, wherein the reconstructed residual block is generated based on: transforming the residual block to generate transform coefficients; quantizing the transform coefficients; de-quantizing the quantized transform coefficients; and inverse transforming the de-quantized transform coefficients. ### Claim 7 (depends on 1) The method of claim 1, wherein the indication of whether the first motion information is the same as the second motion information comprises a one-bit flag. ### Claim 8 (depends on 1) The method of claim 1, wherein, based on the first motion information being the same as the second motion information, the first motion information is signaled as the indication. ### Claim 9 (depends on 1) The method of claim 1, wherein based on the first motion information being different from the second motion information, the method further comprises: entropy encoding the first motion information. ### Claim 10 A non-transitory computer-readable medium storing instructions that, when executed by one or more processors of an encoder, cause the encoder to: determine first motion information, from a plurality of motion information, for a block; determine a residual block based on a difference between the block and a first prediction block that is based on the first motion information; for each respective motion information of the plurality of motion information: generate a reconstructed block based on: a prediction block generated for the respective motion information; and a reconstructed residual block based on the first motion information; and determine a visual quality of the reconstructed block without using the block as a reference; and determine, based on the visual qualities of the reconstructed blocks, second motion information, from the plurality of motion information, as a prediction of the first motion information determined for the block; and signal, in a bitstream, an indication of whether the first motion information is the same as the second motion information. ### Claim 11 (depends on 10) The non-transitory computer-readable medium of claim 10, wherein the second motion information for the block is determined based on the visual quality, among the visual qualities of the reconstructed blocks, with a highest visual quality. ### Claim 12 (depends on 10) The non-transitory computer-readable medium of claim 10, wherein the visual quality of the reconstructed block is determined based on a visual parameter measurement index or a deep Learning for Blind Image Quality Assessment. ### Claim 13 (depends on 10) The non-transitory computer-readable medium of claim 10, wherein: based on the first motion information being the same as the second motion information, the first motion information is signaled as the indication. ### Claim 14 An encoder comprising: one or more processors; and memory storing instructions that, when executed by the one or more processors, cause the encoder to: determine first motion information, from a plurality of motion information, for encoding a block; determine a residual block based on a difference between the block and a first prediction block based on the first motion information; for each respective motion information of the plurality of motion information: generate a reconstructed block based on: a prediction block generated for the respective motion information; and a reconstructed residual block based on the first motion information; and determine a visual quality of the reconstructed block without using the block as a reference; and determine, based on the visual qualities of the reconstructed blocks, second motion information, from the plurality of motion information, as a prediction of the first motion information determined for the block; and signal, in a bitstream, an indication reconstruction of the residual block determined based on the first motion information whether the first motion information is the same as the second motion information. ### Claim 15 (depends on 14) The encoder of claim 14, wherein the second motion information for the block is determined based on the visual quality, among the visual qualities of the reconstructed blocks, with a highest visual quality. ### Claim 16 (depends on 14) The encoder of claim 14, wherein the visual quality of the reconstructed block is determined based on a visual parameter measurement index or a deep Learning for Blind Image Quality Assessment. ### Claim 17 (depends on 14) The encoder of claim 14, wherein: based on the first motion information being the same as the second motion information, the first motion information is signaled as the indication.