公开(公告)号：US20210241426A1

公开(公告)日：2021-08-05

申请号：US16613932

申请日：2017-12-04

Applicant: Google LLC

Inventor： Damien Kelly ,  Neil Birkbeck ,  Balineedu Adsumilli ,  Mohammad Izadi

IPC: G06T5/00

Abstract: A method for denoising video content includes identifying a first frame block associated with a first frame of the video content. The method also includes estimating a first noise model that represents characteristics of the first frame block. The method also includes identifying at least one frame block adjacent to the first frame block. The method also includes generating a second noise model that represents characteristics of the at least one frame block adjacent to the first frame block by adjusting the first noise model based on at least one characteristic of the at least one frame block adjacent to the first frame block. The method also includes denoising the at least one frame block adjacent to the first frame block using the second noise model.

公开(公告)号：US20220237749A1

公开(公告)日：2022-07-28

申请号：US17722720

申请日：2022-04-18

Applicant: Google LLC

Inventor： Neil Birkbeck ,  Balineedu Adsumilli ,  Mohammad Izadi

IPC: G06T5/00

Abstract: Denoising video content includes identifying a three-dimensional flat frame block of multiple frames of the video content, wherein the three-dimensional flat frame block comprises flat frame blocks, each flat frame block is located within a respective frame of the multiple frames, and the flat frame blocks have a spatial and temporal intensity variance that is less than a threshold. Denoising video content also includes determining an average intensity value of the three-dimensional flat frame block, determining a noise model that represents noise characteristics of the three-dimensional flat frame block, generating a denoising function using the average intensity value and the noise model, and denoising the multiple frames using the denoising function.

公开(公告)号：US11962811B2

公开(公告)日：2024-04-16

申请号：US17504886

申请日：2021-10-19

Applicant: GOOGLE LLC

Inventor： Mohammad Izadi ,  Yeping Su ,  Jeremy Dorfman

IPC: H04N19/85 ,  G06T5/00

CPC classification number: H04N19/85 ,  G06T5/002 ,  G06T2207/20021 ,  G06T2207/20064

Abstract: Image denoising includes obtaining a saliency map for an image. The saliency map includes respective saliency scores for pixels of the image. Respective noise levels are assigned to the pixels using the respective saliency scores to obtain a noise level map. The image is denoised using the noise level map to obtain a denoised image. The denoised image is output, such as to a display or a storage device.

公开(公告)号：US11308585B2

公开(公告)日：2022-04-19

申请号：US16613945

申请日：2017-12-05

Applicant: Google LLC

Inventor： Neil Birkbeck ,  Balineedu Adsumilli ,  Mohammad Izadi

IPC: G06T5/00

Abstract: A method for denoising video content includes identifying a first frame block of a plurality of frame blocks associated with a first frame of the video content. The method also includes determining an average intensity value for the first frame block. The method also includes determining a first noise model that represents characteristics of the first frame block. The method also includes generating a denoising function using the average intensity value and the first noise model for the first frame block. The method further includes denoising the plurality of frame blocks using the denoising function.

公开(公告)号：US11854164B2

公开(公告)日：2023-12-26

申请号：US17708983

申请日：2022-03-30

Applicant: Google LLC

Inventor： Damien Kelly ,  Neil Birkbeck ,  Balineedu Adsumilli ,  Mohammad Izadi

IPC: G06T5/00

CPC classification number: G06T5/002 ,  G06T2207/10016 ,  G06T2207/20021

Abstract: Processing a spherical video using denoising is described. Video content comprising the spherical video is received. Whether a camera geometry or a map projection, or both, used to generate the spherical video is available is then determined. The spherical video is denoised using a first technique responsive to a determination that the camera geometry, the map projection, or both is available. Otherwise, the spherical video is denoised using a second technique. At least some steps of the second technique can be different from steps of the first technique. The denoised spherical video can be encoded for transmission or storage using less data than encoding the spherical video without denoising.

公开(公告)号：US11748854B2

公开(公告)日：2023-09-05

申请号：US17722720

申请日：2022-04-18

Applicant: Google LLC

Inventor： Neil Birkbeck ,  Balineedu Adsumilli ,  Mohammad Izadi

IPC: G06T5/00

CPC classification number: G06T5/002 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Denoising video content includes identifying a three-dimensional flat frame block of multiple frames of the video content, wherein the three-dimensional flat frame block comprises flat frame blocks, each flat frame block is located within a respective frame of the multiple frames, and the flat frame blocks have a spatial and temporal intensity variance that is less than a threshold. Denoising video content also includes determining an average intensity value of the three-dimensional flat frame block, determining a noise model that represents noise characteristics of the three-dimensional flat frame block, generating a denoising function using the average intensity value and the noise model, and denoising the multiple frames using the denoising function.

公开(公告)号：US20220078446A1

公开(公告)日：2022-03-10

申请号：US17416235

申请日：2019-04-25

Applicant: Google LLC

Inventor： Mohammad Izadi ,  Balineedu Adsumilli

IPC: H04N19/147 ,  H04N19/117 ,  H04N19/82 ,  H04N19/105 ,  H04N19/176

Abstract: Adaptive filtering is used video stream for bitrate reduction. A first copy of the input video stream is encoded to a reference bitstream. Each of a number of candidate filters is applied to each frame of a second copy of the input video stream to produce a filtered second copy of the input video stream. The filtered second copy is encoded to a candidate bitstream. A cost value for the candidate filter is determined based on distortion value and bitrate differences between the candidate bitstream and the reference bitstream. The candidate bitstream corresponding to the candidate filter with a lowest one of the cost values is selected as the output bitstream, which is then output or stored. Processing the input video stream using the adaptive filter and before the encoding may result in bitrate reduction, thereby improving compression, decompression, and other performance.

公开(公告)号：US12273533B2

公开(公告)日：2025-04-08

申请号：US17416235

申请日：2019-04-25

Applicant: Google LLC

Inventor： Mohammad Izadi ,  Balineedu Adsumilli

IPC: H04N19/147 ,  H04N19/105 ,  H04N19/117 ,  H04N19/176 ,  H04N19/82

Abstract: Adaptive filtering is used video stream for bitrate reduction. A first copy of the input video stream is encoded to a reference bitstream. Each of a number of candidate filters is applied to each frame of a second copy of the input video stream to produce a filtered second copy of the input video stream. The filtered second copy is encoded to a candidate bitstream. A cost value for the candidate filter is determined based on distortion value and bitrate differences between the candidate bitstream and the reference bitstream. The candidate bitstream corresponding to the candidate filter with a lowest one of the cost values is selected as the output bitstream, which is then output or stored. Processing the input video stream using the adaptive filter and before the encoding may result in bitrate reduction, thereby improving compression, decompression, and other performance.

公开(公告)号：US12254603B2

公开(公告)日：2025-03-18

申请号：US17908068

申请日：2020-05-19

Applicant: GOOGLE LLC

Inventor： Mohammad Izadi ,  Pavan Madhusudanarao ,  Balineedu Adsumilli

IPC: G06T5/70 ,  G06T5/20

Abstract: Image data is processed for noise reduction before encoding and subsequent decoding. For an input image in a spatial domain, two-dimensional (2-D) wavelet coefficients at multiple levels are generated. Each level includes multiple subbands, each associated with a respective subband type in a wavelet domain. For respective levels, a flat region of a subband is identified, which flat region includes blocks of the subband having a variance no higher than a first threshold variance. A flat block set for the subband type associated with the subband is identified, which includes blocks common to respective flat regions of the subband. A second threshold variance is determined using variances of the flat block set, and is then used for thresholding at least some of the 2-D wavelet coefficients to remove noise. After thresholding, a denoised image is generated in the spatial domain using the levels.

公开(公告)号：US20240394840A1

公开(公告)日：2024-11-28

申请号：US18669939

申请日：2024-05-21

Applicant: Google LLC

Inventor： Elchonon Zeav Lapin ,  Xibing Yang ,  Amit Handa ,  Apurv Suman ,  Siddhant Mittal ,  Ashish Dilipchand Bora ,  Thorne Wolfenbarger ,  Naga Sreenivas Meruva ,  Yudong Sun ,  Rahul Guin ,  Arie Sharon ,  Beatriz Alessio Robles Orozco ,  Yuanzhen Li ,  Zhongyue Zheng ,  Mohammad Izadi

IPC: G06T5/50 ,  G06T3/40 ,  G06T5/70 ,  G06T7/13 ,  G06T7/194 ,  G06T7/50 ,  H04N5/272

Abstract: Using artificial intelligence (AI), imagery may be created for content in response to verbal or textual input. The imagery includes an object, such as a product, and a quality of the image is improved using pre-processing techniques before the image is generated and post-processing techniques after the image is generated. The pre-processing may include upscaling the object in the original image, segmenting the object from its background in the captured image, adding an outline or border stroke to the object. The post-processing techniques may include removing the object from the AI-generated background while keeping shadows and other effects in place, blurring portions of the AI-generated background where the object will be positioned, removing the outline from the object, and re-positioning the object in the AI-generated background with the outline removed.