公开(公告)号：WO2022014790A1

公开(公告)日：2022-01-20

申请号：PCT/KR2020/015394

申请日：2020-11-05

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： VYAS, Kushal K. ,  LI, Yingmao ,  LUO, Chenchi ,  CHEN, George Q. ,  SHEIKH, Hamid R. ,  YOO, Youngjun ,  POLLEY, Michael O.

IPC: G06T7/55 ,  G06T7/11 ,  G06T1/60 ,  G06T7/40 ,  G06T7/90 ,  G06T5/00 ,  G06N20/00 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T3/40 ,  G06T5/001 ,  G06T7/50 ,  G06T7/70

Abstract: A method includes obtaining, using at least one processor, an input image frame. The method also includes identifying, using the at least one processor, one or more regions of the input image frame containing redundant information. In addition, the method includes performing, using the at least one processor, an image processing task using the input image frame. The image processing task is guided based on the one or more identified regions of the input image frame. The method may further include obtaining, using the at least one processor, a coarse depth map associated with the input image frame. Performing the image processing task may include refining the coarse depth map to produce a refined depth map, where the refining of the coarse depth map is guided based on the one or more identified regions of the input image frame.

公开(公告)号：WO2020176007A1

公开(公告)日：2020-09-03

申请号：PCT/RU2019/000131

申请日：2019-02-27

Applicant: HUAWEI TECHNOLOGIES CO., LTD. ,  EGOROV, Nickolay Dmitrievich

Inventor： ALSHINA, Elena Alexandrovna ,  GILMUTDINOV, Marat Ravilevich ,  NIVIKOV, Dmitry Vadimovich ,  VESELOV, Anton Igorevich ,  MALAKHOV, Kirill Aleksandrovich

IPC: H04N9/64 ,  H04N9/68 ,  H04N9/04 ,  G06N3/04 ,  G06N3/063 ,  G06N3/08 ,  G06T5/00 ,  H04N9/73 ,  G06N3/0454 ,  G06N3/084 ,  G06T2207/10024 ,  G06T2207/20084 ,  G06T5/001 ,  H04N2209/045 ,  H04N9/04551 ,  H04N9/646 ,  H04N9/735

Abstract: The invention relates to an image processing apparatus (100) for processing a color filter mosaic, CFM, image (002) of a scene into a final image (004) of the scene. The image processing apparatus (100) comprises processing circuitry configured to implement a neural network (103), wherein the neural network (103) is configured to process the CFM image (002) into an enhanced CFM image (003), wherein the processing circuitry is further configured to transform the enhanced CFM image (003) into the final image (004). Moreover, the invention relates to a corresponding image processing method.

公开(公告)号：WO2022245640A2

公开(公告)日：2022-11-24

申请号：PCT/US2022/029122

申请日：2022-05-13

Applicant: TENCENT AMERICA LLC

Inventor： JIANG, Wei ,  WANG, Wei ,  XU, Xiaozhong ,  LIU, Shan

IPC: H04N19/154 ,  H04N19/117 ,  G06N3/08 ,  H04N19/172 ,  G06N3/084 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T5/001 ,  G06T5/002 ,  G06T9/002 ,  H04N19/134 ,  H04N19/139 ,  H04N19/159 ,  H04N19/176 ,  H04N19/82

Abstract: A method, apparatus, and non-transitory computer-readable medium for adaptive neural image compression by meta-learning using substitute QF settings, which includes generating one or more substitute quality factors via a plurality of iterations using the original quality factors, wherein the substitute quality factors are a modified version of the original quality factors. The approach may further include determining a neural network based loop filter comprising neural network based loop filter parameters and a plurality of layers, wherein the neural network based loop filter parameters include shared parameters and adaptive parameters, and may further include generating enhanced video data, based on the one or more substitute quality factors and the input video data, using the neural network based loop filter.

公开(公告)号：WO2022241410A1

公开(公告)日：2022-11-17

申请号：PCT/US2022/072220

申请日：2022-05-09

Applicant: NEP SUPERSHOOTERS, L.P.

Inventor： CHOFFAT, Casper Philippe Henri ,  SCRUTCHFIELD, Todd Neville ,  COLLINS, Alan ,  CHOY, Justin Ming Yuan ,  ZHANG, Yufei

IPC: A61B17/32 ,  G06T5/001 ,  G06T7/20 ,  H04N5/23206 ,  H04N5/23299

Abstract: A system. The system includes an image display system, a display device, a camera system, one or more control devices and a control system. The display device is configured to display an image received from the image display system. The camera system is configured to capture the image displayed by the display device during a capture of a scene. The control system is communicably coupled to the image display system, the display device, the camera system and the one or more control devices. The control system comprises a processing circuit and is configured to automatically adjust settings of the image display system, the display device and the camera system. The control system is also configured to determine which of the adjustments results in the least destruction to the image, and apply the adjustment which results in the least destruction to the image.

公开(公告)号：WO2021146576A1

公开(公告)日：2021-07-22

申请号：PCT/US2021/013667

申请日：2021-01-15

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： MAYOL CUEVAS, Walterio Wolfgang ,  BOKHARI, Wasiq ,  VASS, William ,  LOVE, Sean ,  SOOD, Garish

IPC: H04N21/234 ,  G06T3/40 ,  G06T5/00 ,  H04N19/117 ,  H04N21/845 ,  G06K9/00718 ,  G06N20/00 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T3/4053 ,  G06T5/001 ,  H04L65/601 ,  H04L65/608 ,  H04N21/2187 ,  H04N21/23418 ,  H04N21/2402 ,  H04N21/2662 ,  H04N21/8456

Abstract: Techniques for video enhancement using a service are described. A video enhancement service is to receive, from a requesting device, a request to provide a video (412), the request including an indication that at least a proper subset of the video is to be enhanced using at least one machine learning model; select at least one machine learning model to be used to enhance at least the proper subset of the video (417); enhance at least the proper subset of the video using the selected at least one machine learning model (418); and output the video including the at least proper subset of the video that had been enhanced (419).

公开(公告)号：WO2022241368A1

公开(公告)日：2022-11-17

申请号：PCT/US2022/071768

申请日：2022-04-18

Applicant: PAIGE.AL, INC.

Inventor： ALEMI, Navid ,  KANAN, Christopher ,  GRADY, Leo

IPC: G06T7/00 ,  G16H30/40 ,  G01N1/30 ,  G06T2207/10056 ,  G06T2207/20084 ,  G06T5/001 ,  G06V10/454 ,  G06V10/56 ,  G06V10/82 ,  G06V20/695 ,  G16H50/20

Abstract: Systems and methods are disclosed for adjusting attributes of whole slide images, including stains therein. A portion of a whole slide image comprised of a plurality of pixels in a first color space and including one or more stains may be received as input. Based on an identified stain type of the stain(s), a machine- learned transformation associated with the stain type may be retrieved and applied to convert an identified subset of the pixels from the first to a second color space specific to the identified stain type. One or more attributes of the stain(s) may be adjusted in the second color space to generate a stain-adjusted subset of pixels, which are then converted back to the first color space using an inverse of the machine-learned transformation. A stain-adjusted portion of the whole slide image including at least the stain-adjusted subset of pixels may be provided as output.

公开(公告)号：WO2021246821A1

公开(公告)日：2021-12-09

申请号：PCT/KR2021/007012

申请日：2021-06-04

Applicant: 주식회사 픽스트리

Inventor： 신재섭 ,  류성걸 ,  손세훈 ,  김형덕 ,  김효성 ,  고경환

IPC: G06T5/00 ,  G06T3/00 ,  G06T3/40 ,  G06T3/60 ,  G06T7/33 ,  G06T2207/20101 ,  G06T2207/30201 ,  G06T3/0093 ,  G06T5/001

Abstract: 본 실시예는 입력 이미지로부터 검출된 바운딩 박스 내의 얼굴의 랜드마크의 위치를 검출하고, 랜드마크를 기반으로 정면 얼굴이 중앙 혹은 기준 위치에 위치하도록 정렬하는 와핑을 수행한 상태에서 정면 얼굴 영상으로 학습한 학습 모델을 이용하여 영상을 개선시키고, 개선된 영상을 다시 원래의 방향이나 각도로 회전시키는 인버스 와핑을 수행한 후 입력 이미지 내에 삽입하여 보다 자연스러운 영상을 복원이 가능하도록 하는 얼굴 이미지 복원 방법 및 장치를 제공한다. 또한, 본 실시예는 입력 이미지로부터 검출된 바운딩 박스 내의 얼굴에 대한 포즈 추정을 수행하고, 포즈 추정 결과에 대응하는 측면 얼굴 영상으로 학습한 학습 모델을 이용하여 영상을 개선시키는 얼굴 이미지 복원 방법 및 장치를 제공한다.

公开(公告)号：WO2021132798A1

公开(公告)日：2021-07-01

申请号：PCT/KR2020/002088

申请日：2020-02-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： JEPSON, Allan ,  LEVINSHTEIN, Aleksai ,  KEMERTAS, Mete ,  ZHANG, Haotian ,  REZAEE KAVIANI, Hoda

IPC: G06T1/20 ,  G06T1/60 ,  G06T9/00 ,  G06F21/62 ,  G06T5/20 ,  G06F21/6254 ,  G06F2221/2113 ,  G06N20/20 ,  G06N3/0454 ,  G06N3/084 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T5/001

Abstract: An apparatus for scrubbing an image may include a memory storing instructions; and a processor configured to execute the instructions to: receive an input image; input a preset public attribute to an encoder neural network; obtain a scrubbed feature from the input image based on the preset public attribute, via the encoder neural network; wherein the encoder neural network is trained based on an amount of information in the scrubbed feature about the input image, and an estimated public attribute estimated from the scrubbed feature.

公开(公告)号：WO2021029423A2

公开(公告)日：2021-02-18

申请号：PCT/JP2020/030707

申请日：2020-08-12

Applicant: RICOH COMPANY, LTD. ,  ZHANG, Yupeng ,  LI, Daojing ,  ODAMAKI, Makoto ,  YI, Hong ,  LIU, Liyan ,  JIA, Huan ,  WANG, Wei

Inventor： ZHANG, Yupeng ,  LI, Daojing ,  ODAMAKI, Makoto ,  YI, Hong ,  LIU, Liyan ,  JIA, Huan ,  WANG, Wei

IPC: G06T3/00 ,  G06T3/40 ,  G06T5/00 ,  G06K9/6202 ,  G06T2207/10004 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20221 ,  G06T2207/30168 ,  G06T3/0062 ,  G06T3/4046 ,  G06T3/4076 ,  G06T5/001 ,  G06T7/11

Abstract: Disclosed is an image processing method including steps of obtaining a plurality of sets of training data, each set of training data containing data of first and second images, image quality of the second image being higher than that of the first image, shooting contents of the first image being the same as shooting contents of the second image; constructing an image enhancement model, letting the data of the first image be an input of the model, and utilizing the plurality of sets of training data to train the model until a difference feature value between an output of the model and the data of the second image is minimum; and inputting data of a third image to be processed into the model so as to output data of a fourth image after image enhancement, image quality of the fourth image being higher than that of the third image.

公开(公告)号：WO2022271291A1

公开(公告)日：2022-12-29

申请号：PCT/US2022/029083

申请日：2022-05-13

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： JOZE, Hamidreza Vaezi

IPC: G06T7/90 ,  G06T5/00 ,  G06N20/00 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T5/001 ,  G06T5/007 ,  G06T5/50 ,  G06T7/11 ,  G06T7/174 ,  G06V10/60

Abstract: An image processor receives first image data representing an image. The first image data comprising a plurality of color values corresponding to a plurality of pixels in the image. The image processor determines, using a trained machine learning model, second image data based on the first image data. The second image data comprises surface spectral reflection values corresponding to the plurality of pixels in the image, where the surface spectral reflection values are distributed across a plurality of wavelengths of visible light in the image. The image processor then performs at least one image processing operation with respect to the image using the second image data.