Patents by Inventor Anand Kotra
Anand Kotra has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11930215Abstract: An example device for filtering decoded video data includes a memory configured to store video data; and one or more processors implemented in circuitry and configured to: decode a picture of video data; code a value for a syntax element representing a neural network model to be used to filter a portion of the decoded picture, the value representing an index into a set of pre-defined neural network models, the index corresponding to the neural network model in the set of pre-defined neural network models; and filter the portion of the decoded picture using the neural network model corresponding to the index.Type: GrantFiled: September 23, 2021Date of Patent: March 12, 2024Assignee: QUALCOMM IncorporatedInventors: Hongtao Wang, Venkata Meher Satchit Anand Kotra, Jianle Chen, Marta Karczewicz, Dana Kianfar, Auke Joris Wiggers
-
Patent number: 11825101Abstract: An example device for decoding video data includes a memory configured to store video data; and one or more processors implemented in circuitry and configured to: apply a downsampling convolutional neural network layer to a first color component of a block of video data, the first color component of the block having a first size, wherein applying the downsampling convolutional neural network layer to the first color component generates a downsampled first color component having a second size smaller than the first size; filter a second color component having the second size to form a filtered second color component; concatenate the downsampled first color component with the filtered second color component to form concatenated color components; and filter the concatenated color components to form a filtered concatenated component including a filtered downsampled first color component.Type: GrantFiled: October 4, 2021Date of Patent: November 21, 2023Assignee: QUALCOMM IncorporatedInventors: Jianle Chen, Hongtao Wang, Venkata Meher Satchit Anand Kotra, Marta Karczewicz
-
Publication number: 20230336734Abstract: An example device for decoding video data includes a memory configured to store video data; and one or more processors implemented in circuitry and configured to: decode a current block of the video data to form a decoded block; determine that a current sample of the decoded block neighbors a sample along a virtual boundary in the decoded block and neighbors one or more samples that are not along any virtual boundary in the decoded block; compute band information for cross component sample adaptive offset (CCSAO) for the current sample using at least one of the one or more samples that are not along any virtual boundary in the decoded block and without using the sample along the virtual boundary; and perform CCSAO on the current sample using the band information.Type: ApplicationFiled: April 11, 2023Publication date: October 19, 2023Inventors: Venkata Meher Satchit Anand Kotra, Nan Hu, Vadim Seregin, Marta Karczewicz
-
Publication number: 20230300328Abstract: A device for decoding video data determines a pre-filtered reconstructed block of video data; applies one or more of a deblocking filter or a sample adaptive offset filter to the pre-filtered reconstructed block to determine a filtered reconstructed block; applies an adaptive loop filter (ALF) to the filtered reconstructed block to determine a final filtered reconstructed block, wherein to apply the ALF to the filtered reconstructed block, the device is further configured to determine a difference value based on a difference between a value of a current sample of the filtered reconstructed block and a value of a pre-filtered neighboring sample; apply a filter to the difference value to determine a sample modification value; and determine a final filtered sample value based on the sample modification value.Type: ApplicationFiled: March 9, 2023Publication date: September 21, 2023Inventors: Nan Hu, Vadim Seregin, Venkata Meher Satchit Anand Kotra, Marta Karczewicz
-
Publication number: 20230283772Abstract: An example device for filtering decoded video data includes a memory configured to store video data; and one or more processors implemented in circuitry and configured to: decode a block of video data to form a decoded block; apply a filter to the decoded block to form a filtered block; multiply samples of the filtered block by a scaling factor to form a refined filtered block; and combine samples of the refined filtered block with corresponding samples of the decoded block. The one or more processors may further encode the block prior to decoding the block. The one or more processors may encode or decode a value of a syntax element representing the scaling factor, e.g., in a picture header of a picture including the block.Type: ApplicationFiled: May 11, 2023Publication date: September 7, 2023Inventors: Marta Karczewicz, Hongtao Wang, Jianle Chen, Venkata Meher Satchit Anand Kotra
-
Patent number: 11743459Abstract: An example device for filtering decoded video data includes a memory configured to store video data; and one or more processors implemented in circuitry and configured to: decode a block of video data to form a decoded block; apply a filter to the decoded block to form a filtered block; multiply samples of the filtered block by a scaling factor to form a refined filtered block; and combine samples of the refined filtered block with corresponding samples of the decoded block. The one or more processors may further encode the block prior to decoding the block. The one or more processors may encode or decode a value of a syntax element representing the scaling factor, e.g., in a picture header of a picture including the block.Type: GrantFiled: September 23, 2021Date of Patent: August 29, 2023Assignee: QUALCOMM INCORPORATEDInventors: Marta Karczewicz, Hongtao Wang, Jianle Chen, Venkata Meher Satchit Anand Kotra
-
Publication number: 20230101318Abstract: Systems and techniques are described for processing video data. For instance, a process can include obtaining video data. The process can further include determining a classification band for a first sample of the video data using at least chroma information from the first sample, collocated luma information and collocated chroma information. The process can also include filtering at least the first sample of the video data based on the classification band.Type: ApplicationFiled: September 7, 2022Publication date: March 30, 2023Inventors: Venkata Meher Satchit Anand KOTRA, Nan HU, Vadim SEREGIN, Marta KARCZEWICZ
-
Publication number: 20220400292Abstract: A video encoder or video decoder are configured to reconstruct the video data to generate reconstructed video data. The video encoder or video decoder may further perform a plurality of loop filter operations on the reconstructed video data in parallel, wherein the plurality of loop filter operations includes a first filter operation that is not a bilateral filter operation or a sample adaptive offset (SAO) filter operation, and perform a joint clipping operation on a first output of the first filter and a second output of a second loop filter operation of the plurality of loop filter operations. The first filter operation may be a cross-component sample adaptive offset (CCSAO) filter operation.Type: ApplicationFiled: June 9, 2022Publication date: December 15, 2022Inventors: Venkata Meher Satchit Anand Kotra, Nan Hu, Vadim Seregin, Marta Karczewicz
-
Publication number: 20220215593Abstract: An example device for filtering decoded video data includes one or more processors configured to execute a neural network filtering unit to: receive data from one or more other units of the device, the data from the one or more other units of the device being different than data for a decoded picture of video data, and wherein to receive the data from the one or more other units of the device, the one or more processors are configured to execute the neural network filtering unit to receive boundary strength data from a deblocking unit of the device; determine one or more neural network models to be used to filter a portion of the decoded picture; and filter the portion of the decoded picture using the one or more neural network models and the data from the one or more other units of the device, including the boundary strength data.Type: ApplicationFiled: December 30, 2021Publication date: July 7, 2022Inventors: Hongtao Wang, Venkata Meher Satchit Anand Kotra, Jianle Chen, Marta Karczewicz
-
Publication number: 20220109860Abstract: An example device for decoding video data includes a memory configured to store video data; and one or more processors implemented in circuitry and configured to: apply a downsampling convolutional neural network layer to a first color component of a block of video data, the first color component of the block having a first size, wherein applying the downsampling convolutional neural network layer to the first color component generates a downsampled first color component having a second size smaller than the first size; filter a second color component having the second size to form a filtered second color component; concatenate the downsampled first color component with the filtered second color component to form concatenated color components; and filter the concatenated color components to form a filtered concatenated component including a filtered downsampled first color component.Type: ApplicationFiled: October 4, 2021Publication date: April 7, 2022Inventors: Jianle Chen, Hongtao Wang, Venkata Meher Satchit Anand Kotra, Marta Karczewicz
-
Publication number: 20220103864Abstract: An example device for filtering decoded video data includes a memory configured to store video data; and one or more processors implemented in circuitry and configured to: decode a picture of video data; code a value for a syntax element representing a neural network model to be used to filter a portion of the decoded picture, the value representing an index into a set of pre-defined neural network models, the index corresponding to the neural network model in the set of pre-defined neural network models; and filter the portion of the decoded picture using the neural network model corresponding to the index.Type: ApplicationFiled: September 23, 2021Publication date: March 31, 2022Inventors: Hongtao Wang, Venkata Meher Satchit Anand Kotra, Jianle Chen, Marta Karczewicz, Dana Kianfar, Auke Joris Wiggers
-
Publication number: 20220103816Abstract: An example device for filtering decoded video data includes a memory configured to store video data; and one or more processors implemented in circuitry and configured to: decode a block of video data to form a decoded block; apply a filter to the decoded block to form a filtered block; multiply samples of the filtered block by a scaling factor to form a refined filtered block; and combine samples of the refined filtered block with corresponding samples of the decoded block. The one or more processors may further encode the block prior to decoding the block. The one or more processors may encode or decode a value of a syntax element representing the scaling factor, e.g., in a picture header of a picture including the block.Type: ApplicationFiled: September 23, 2021Publication date: March 31, 2022Inventors: Marta Karczewicz, Hongtao Wang, Jianle Chen, Venkata Meher Satchit Anand Kotra
-
Publication number: 20220030255Abstract: The present disclosure relates to deblocking filtering which is applicable to smoothing the block boundaries in an image or video coding and decoding. In particular, the deblocking filtering is either strong or weak, wherein the clipping is performed differently in the strong filtering and the weak filtering.Type: ApplicationFiled: October 12, 2021Publication date: January 27, 2022Inventors: Matthias NARROSCHKE, Anand KOTRA, Semih ESENLIK, Thomas WEDI
-
Patent number: 11178425Abstract: The present disclosure relates to deblocking filtering which is applicable to smoothing the block boundaries in an image or video coding and decoding. In particular, the deblocking filtering is either strong or weak, wherein the clipping is performed differently in the strong filtering and the weak filtering.Type: GrantFiled: April 13, 2020Date of Patent: November 16, 2021Assignee: SUN PATENT TRUSTInventors: Matthias Narroschke, Anand Kotra, Semih Esenlik, Thomas Wedi
-
Patent number: 10958935Abstract: The present disclosure relates to deblocking filtering which is applicable to smoothing the block boundaries in an image or video coding and decoding. In particular, the deblocking filtering is either strong or weak, wherein the clipping is performed differently in the strong filtering and the weak filtering.Type: GrantFiled: October 15, 2018Date of Patent: March 23, 2021Assignee: SUN PATENT TRUSTInventors: Matthias Narroschke, Anand Kotra, Semih Esenlik, Thomas Wedi
-
Publication number: 20200244988Abstract: The present disclosure relates to deblocking filtering which is applicable to smoothing the block boundaries in an image or video coding and decoding. In particular, the deblocking filtering is either strong or weak, wherein the clipping is performed differently in the strong filtering and the weak filtering.Type: ApplicationFiled: April 13, 2020Publication date: July 30, 2020Inventors: Matthias NARROSCHKE, Anand KOTRA, Semih ESENLIK, Thomas WEDI
-
Patent number: 10659809Abstract: The present disclosure relates to deblocking filtering which is applicable to smoothing the block boundaries in an image or video coding and decoding. In particular, the deblocking filtering is either strong or weak, wherein the clipping is performed differently in the strong filtering and the weak filtering.Type: GrantFiled: October 15, 2018Date of Patent: May 19, 2020Assignee: SUN PATENT TRUSTInventors: Matthias Narroschke, Anand Kotra, Semih Esenlik, Thomas Wedi
-
Patent number: 10375417Abstract: The present invention relates to an advantageous scheme for boundary strength derivation and decision processing related to deblocking filtering. More particularly, the present invention improves schemes for deciding deblocking and selecting appropriate deblocking filters known in the art so as to reduce the number of calculation cycles and required memory space.Type: GrantFiled: December 13, 2018Date of Patent: August 6, 2019Assignee: Sun Patent TrustInventors: Thomas Wedi, Anand Kotra, Matthias Narroschke, Semih Esenlik
-
Publication number: 20190116384Abstract: The present invention relates to an advantageous scheme for boundary strength derivation and decision processing related to deblocking filtering. More particularly, the present invention improves schemes for deciding deblocking and selecting appropriate deblocking filters known in the art so as to reduce the number of calculation cycles and required memory space.Type: ApplicationFiled: December 13, 2018Publication date: April 18, 2019Inventors: Thomas WEDI, Anand KOTRA, Matthias NARROSCHKE, Semih ESENLIK
-
Publication number: 20190052895Abstract: The present disclosure relates to deblocking filtering which is applicable to smoothing the block boundaries in an image or video coding and decoding. In particular, the deblocking filtering is either strong or weak, wherein the clipping is performed differently in the strong filtering and the weak filtering.Type: ApplicationFiled: October 15, 2018Publication date: February 14, 2019Inventors: Matthias NARROSCHKE, Anand KOTRA, Semih ESENLIK, Thomas WEDI