专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20220215588A1 IMAGE SIGNAL PROCESSOR FOR PROCESSING IMAGES 有权
公开(公告)号：US20220215588A1
公开(公告)日：2022-07-07
申请号：US17665281
申请日：2022-02-04
申请人： QUALCOMM Incorporated
发明人： Hau HWANG , Tushar Sinha PANKAJ , Vishal GUPTA , Jisoo LEE
IPC分类号： G06T7/90 , G06T3/00 , G06N3/04 , G06N20/00 , G06T3/40
摘要： Techniques are provided for using one or more machine learning systems to process input data including image data. The input data including the image data can be obtained, and at least one machine learning system can be applied to at least a portion of the image data to determine at least one color component value for one or more pixels of at least the portion of the image data. Based on application of the at least one machine learning system to at least the portion of the image data, output image data for a frame of output image data can be generated. The output image data includes at least one color component value for one or more pixels of the frame of output image data. Application of the at least one machine learning system causes the output image data to have a reduced dimensionality relative to the input data.

2. 发明公开

US20230388623A1 COMPOSITE IMAGE SIGNAL PROCESSOR 审中-公开
公开(公告)号：US20230388623A1
公开(公告)日：2023-11-30
申请号：US18447978
申请日：2023-08-10
申请人： QUALCOMM Incorporated
发明人： Hau HWANG , Shusil DANGI
IPC分类号： H04N23/62 , G06T3/40 , H04N23/80
CPC分类号： H04N23/62 , G06T3/4015 , H04N23/80
摘要： Systems and techniques are described for image processing. An imaging system can include an image sensor that captures image data. An image signal processor (ISP) of the imaging system can demosaic the image data. The imaging system can input the image data into one or more trained machine learning models, in some cases along with metadata associated with the image data. The one or more trained machine learning models can output settings for a set of parameters of the ISP based on the image data and/or the metadata. The imaging system can generate an output image by processing the image data using the ISP, with the parameters of the ISP set according to the settings. Each pixel of the pixels of the image data can be processed using a respective setting for adjusting a corresponding parameter. The parameters of the ISP can include gain, offset, gamma, and Gaussian filtering.

3. 发明公开

US20240303781A1 SYSTEMS AND METHODS FOR RUNTIME NETWORK ADJUSTMENT 审中-公开
公开(公告)号：US20240303781A1
公开(公告)日：2024-09-12
申请号：US18182255
申请日：2023-03-10
申请人： QUALCOMM Incorporated
发明人： Hau HWANG
IPC分类号： G06T5/00 , G06T7/90 , H04N23/76 , H04N23/86
CPC分类号： G06T5/70 , G06T5/73 , G06T5/92 , G06T7/90 , H04N23/76 , H04N23/86 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084
摘要： Sensor data processing systems and techniques are described. In some examples, a sensor data processing system receives sensor data (e.g., image data). The system receives a sensor data processing parameter that is associated with a sensor data processing function, such as denoising, and that is consistent across the sensor data. The system adjusts a trained machine learning model based on the sensor data processing parameter to generate an adjusted machine learning model. The system processes the sensor data using the adjusted machine learning model to apply the sensor data processing function to the sensor data according to the sensor data processing parameter and to generate processed sensor data (e.g., denoised image data).

4. 发明申请

US20210360179A1 MACHINE LEARNING BASED IMAGE ADJUSTMENT 有权
公开(公告)号：US20210360179A1
公开(公告)日：2021-11-18
申请号：US17316567
申请日：2021-05-10
申请人： QUALCOMM Incorporated
发明人： Shusil DANGI , Hau HWANG , Venkata Ravi Kiran DAYANA
IPC分类号： H04N5/357 , H04N9/64 , H04N9/68 , G06T5/00
摘要： An imaging system can obtain image data, for instance from an image sensor. The imaging system can supply the image data as input data to a machine learning system, which can generate one or more maps based on the image data. Each map can identify strengths at which a certain image processing function is to be applied to each pixel of the image data. Different maps can be generated for different image processing functions, such as noise reduction, sharpening, or color saturation. The imaging system can generate a modified image based on the image data and the one or more maps, for instance by applying each of one or more image processing functions in accordance with each of the one or more maps. The imaging system can supply the image data and the one or more maps to a second machine learning system to generate the modified image.

5. 发明公开

US20240054681A1 IMAGE SIGNAL PROCESSOR FOR PROCESSING IMAGES 审中-公开
公开(公告)号：US20240054681A1
公开(公告)日：2024-02-15
申请号：US18494099
申请日：2023-10-25
申请人： QUALCOMM Incorporated
发明人： Hau HWANG , Tushar Sinha PANKAJ , Vishal GUPTA , Jinsoo LEE
IPC分类号： G06T7/90 , G06T3/00 , G06N3/04 , G06N20/00 , G06T3/40
CPC分类号： G06T7/90 , G06T3/0031 , G06N3/04 , G06N20/00 , G06T3/4015 , G06T2207/20084
摘要： Techniques are provided for using one or more machine learning systems to process input data including image data. The input data including the image data can be obtained, and at least one machine learning system can be applied to at least a portion of the image data to determine at least one color component value for one or more pixels of at least the portion of the image data. Based on application of the at least one machine learning system to at least the portion of the image data, output image data for a frame of output image data can be generated. The output image data includes at least one color component value for one or more pixels of the frame of output image data. Application of the at least one machine learning system causes the output image data to have a reduced dimensionality relative to the input data.

6. 发明申请

US20200211229A1 IMAGE SIGNAL PROCESSOR FOR PROCESSING IMAGES 审中-公开
公开(公告)号：US20200211229A1
公开(公告)日：2020-07-02
申请号：US16814783
申请日：2020-03-10
申请人： QUALCOMM Incorporated
发明人： Hau HWANG , Tushar Sinha PANKAJ , Vishal GUPTA , Jisoo LEE
IPC分类号： G06T7/90 , G06T3/00 , G06T3/40 , G06N3/04 , G06N20/00
摘要： Techniques are provided for using one or more machine learning systems to process input data including image data. The input data including the image data can be obtained, and at least one machine learning system can be applied to at least a portion of the image data to determine at least one color component value for one or more pixels of at least the portion of the image data. Based on application of the at least one machine learning system to at least the portion of the image data, output image data for a frame of output image data can be generated. The output image data includes at least one color component value for one or more pixels of the frame of output image data. Application of the at least one machine learning system causes the output image data to have a reduced dimensionality relative to the input data.

7. 发明申请

US20220408012A1 COMPOSITE IMAGE SIGNAL PROCESSOR 有权
公开(公告)号：US20220408012A1
公开(公告)日：2022-12-22
申请号：US17351967
申请日：2021-06-18
申请人： QUALCOMM Incorporated
发明人： Hau HWANG , Shusil DANGI
IPC分类号： H04N5/232 , G06T3/40
摘要： Systems and techniques are described for image processing. An imaging system can include an image sensor that captures image data. An image signal processor (ISP) of the imaging system can demosaic the image data. The imaging system can input the image data into one or more trained machine learning models, in some cases along with metadata associated with the image data. The one or more trained machine learning models can output settings for a set of parameters of the ISP based on the image data and/or the metadata. The imaging system can generate an output image by processing the image data using the ISP, with the parameters of the ISP set according to the settings. Each pixel of the pixels of the image data can be processed using a respective setting for adjusting a corresponding parameter. The parameters of the ISP can include gain, offset, gamma, and Gaussian filtering.

8. 发明申请

US20220101133A1 DYNAMIC QUANTIZATION FOR ENERGY EFFICIENT DEEP LEARNING 有权
公开(公告)号：US20220101133A1
公开(公告)日：2022-03-31
申请号：US17488261
申请日：2021-09-28
申请人： QUALCOMM Incorporated
发明人： Randy ARDYWIBOWO , Venkata Ravi Kiran DAYANA , Hau HWANG
IPC分类号： G06N3/08 , G06N3/04 , G06K9/62
摘要： A method performed by a deep neural network (DNN) includes receiving, at a layer of the DNN during an inference stage, a layer input comprising content associated with a DNN input received at the DNN. The method also includes quantizing one or more parameters of a plurality of parameters associated with the layer based on the content of the layer input. The method further includes performing a task corresponding to the DNN input, the task performed with the one or more one quantized parameters.

9. 发明申请

US20190108618A1 IMAGE SIGNAL PROCESSOR FOR PROCESSING IMAGES 审中-公开
公开(公告)号：US20190108618A1
公开(公告)日：2019-04-11
申请号：US15993223
申请日：2018-05-30
申请人： QUALCOMM Incorporated
发明人： Hau HWANG , Tushar Sinha PANKAJ , Vishal GUPTA , Jisoo LEE
IPC分类号： G06T3/40 , G06N3/08
摘要： Techniques and systems are provided for processing image data using one or more neural networks. For example, a patch of raw image data can be obtained. The patch can include a subset of pixels of a frame of raw image data, and the frame can be captured using one or more image sensors. The patch of raw image data includes a single color component for each pixel of the subset of pixels. At least one neural network can be applied to the patch of raw image data to determine a plurality of color component values for one or more pixels of the subset of pixels. A patch of output image data can then be generated based on application of the at least one neural network to the patch of raw image data. The patch of output image data includes a subset of pixels of a frame of output image data, and also includes the plurality of color component values for one or more pixels of the subset of pixels of the frame of output image data. Application of the at least one neural network causes the patch of output image data to include fewer pixels than the patch of raw image data. Multiple patches from the frame can be processed by the at least one neural network in order to generate a final output image. In some cases, the patches from the frame can be overlapping so that the final output image contains a complete picture.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式