公开(公告)号：US20240135505A1

公开(公告)日：2024-04-25

申请号：US18373710

申请日：2023-09-27

Applicant: Imagination Technologies Limited

Inventor： James Imber ,  Joseph Heyward ,  Kristof Beets

IPC: G06T5/73 ,  G06T3/4053

CPC classification number: G06T5/73 ,  G06T3/4053

Abstract: Methods and processing modules apply adaptive sharpening, for a block of input pixels, to determine a block of output pixels. A block of sharp pixels is obtained based on the block of input pixels, the block of sharp pixels being for representing a sharp version of the block of output pixels. One or more indications of contrast for the block of input pixels is determined. Each of the output pixels of the block of output pixels is determined by performing a respective weighted sum of: (i) a corresponding input pixel in the block of input pixels and (ii) a corresponding sharp pixel in the block of sharp pixels. The weights of the weighted sums are based on the determined one or more indications of contrast for the block of input pixels.

公开(公告)号：US20240126073A1

公开(公告)日：2024-04-18

申请号：US18376466

申请日：2023-10-04

Applicant: Technion Research & Development Foundation Limited

Inventor： Yoav SHECHTMAN ,  Nadav OPATOVSKI

IPC: G02B27/00 ,  G06T5/20 ,  G06T5/73

CPC classification number: G02B27/0025 ,  G06T5/20 ,  G06T5/73

Abstract: In a range imaging system, a passive optical system has a set of lenses and an optical mask that varies a point spread function of the set of lenses so as to encode in an optical field arriving from a scene range information for objects in the scene that are at least X meters from the mask, where X is at least 10. A digital light sensor receives the optical field, and an image processor processes signals receive signals from the sensor to decode the range information.

公开(公告)号：US11933993B2

公开(公告)日：2024-03-19

申请号：US17451450

申请日：2021-10-19

Applicant: Hitachi, Ltd.

Inventor： Takeshi Shimano

IPC: G02B3/00 ,  H04N23/80

CPC classification number: G02B3/0056 ,  G06T5/73 ,  H04N23/80

Abstract: An imaging optical system includes an optical component having a plurality of annular grooves formed to provide a phase to optical ray propagating an effective pupil, the phase causing the longitudinal aberration of the optical ray to alternate plural times to zigzag, and therefore, a focal-depth extended image being clear and having a large focal depth in a uniform image quality is achieved in a wide defocus range in front and back of a focal point.

公开(公告)号：US12131446B2

公开(公告)日：2024-10-29

申请号：US17368534

申请日：2021-07-06

Applicant: GE Precision Healthcare LLC

Inventor： Rajesh Veera Venkata Lakshmi Langoju ,  Prasad Sudhakara Murthy ,  Utkarsh Agrawal ,  Bhushan D. Patil ,  Bipul Das

IPC: G06T5/73 ,  G06N20/00 ,  G06T3/4053 ,  G06T5/20

CPC classification number: G06T5/73 ,  G06N20/00 ,  G06T3/4053 ,  G06T5/20 ,  G06T2207/20081

Abstract: Systems/techniques that facilitate self-supervised deblurring are provided. In various embodiments, a system can access an input image generated by an imaging device. In various aspects, the system can train, in a self-supervised manner based on a point spread function of the imaging device, a machine learning model to deblur the input image. More specifically, the system can append to the model one or more non-trainable convolution layers having a blur kernel that is based on the point spread function of the imaging device. In various aspects, the system can feed the input image to the model, the model can generate a first output image based on the input image, the one or more non-trainable convolution layers can generate a second output image by convolving the first output image with the blur kernel, and the system can update parameters of the model based on a difference between the input image and the second output image.

公开(公告)号：US20240354900A1

公开(公告)日：2024-10-24

申请号：US18630036

申请日：2024-04-09

Applicant: CANON KABUSHIKI KAISHA

Inventor： KAZUKI SATO

IPC: G06T5/50 ,  G06T5/70 ,  G06T5/73

CPC classification number: G06T5/50 ,  G06T5/70 ,  G06T5/73 ,  G06T2207/20221

Abstract: An image processing apparatus includes a first acquisition unit configured to acquire a plurality of RAW images obtained by continuously capturing a subject, a combining unit configured to combine the plurality of RAW images to generate a combined RAW image, a second acquisition unit configured to acquire first information regarding a noise signal level in any of the plurality of RAW images not combined by the combining unit, a third acquisition unit configured to acquire second information regarding a noise signal level in the combined RAW image after the combine by the combining unit, and a determination unit configured to determine a development parameter for developing the combined RAW image based on capturing sensitivity of a capturing element when the plurality of RAW images are captured and the first information and the second information.

公开(公告)号：US12125179B2

公开(公告)日：2024-10-22

申请号：US17755190

申请日：2020-11-10

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yonghuan David Ren ,  Timothy Andrew Large ,  Neil Emerton ,  Yuqian Zhou

IPC: G06T5/00 ,  G06T5/73 ,  H04N5/225 ,  H04N23/56

CPC classification number: G06T5/73 ,  H04N23/56 ,  G06T2207/20081

Abstract: An electronic device comprises a display, an illumination source, a camera, and a logic system. The illumination source is configured to project structured illumination onto a subject. The camera is configured to image the subject through the display, which includes collecting the structured illumination as reflected by the subject. The logic system is configured to receive, from the camera, a digital image of the subject imaged through the display. The logic system is further configured to sharpen the digital image based on the spatially resolved intensity of the structured illumination as reflected by the subject.

公开(公告)号：US12123951B1

公开(公告)日：2024-10-22

申请号：US17733227

申请日：2022-04-29

Applicant: BAE SYSTEMS INFORMATION AND ELECTRONIC SYSTEMS INTEGRATION INC.

Inventor： Michael J. DeWeert ,  Eric M. Louchard ,  Reid A. Noguchi ,  Gary Sawai ,  Dugan C. Yoon

IPC: G01S17/89 ,  G01J4/04 ,  G01S7/4861 ,  G06T5/73

CPC classification number: G01S17/89 ,  G01J4/04 ,  G01S7/4861 ,  G06T5/73 ,  G06T2207/20201

Abstract: A system and method is provided to characterize optical properties (Scattering, attenuation, de-polarization) of a light-transmitting medium and local environment, by determining a scattering rate of light through a medium, wherein determining the scattering rate of light through the medium is accomplished by utilizing polarized light transmitted from an optical source. The system and method performs a function based on the characterized optical properties of the medium, wherein the function is one of, for example: detection of objects embedded in the medium, object ranging through the medium, or deblurring of images acquired through the medium.

公开(公告)号：US20240346629A1

公开(公告)日：2024-10-17

申请号：US18301671

申请日：2023-04-17

Applicant: ADOBE INC.

Inventor： Midhun Harikumar ,  Venkata Naveen Kumar Yadav Marri ,  Ajinkya Gorakhnath Kale ,  Pranav Vineet Aggarwal ,  Vinh Ngoc Khuc

IPC: G06T5/00 ,  G06F40/279 ,  G06T5/50

CPC classification number: G06T5/73 ,  G06F40/279 ,  G06T5/50

Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure obtain a text prompt for text guided image generation. A multi-modal encoder of an image processing apparatus encodes the text prompt to obtain a text embedding. A diffusion prior model of the image processing apparatus converts the text embedding to an image embedding. A latent diffusion model of the image processing apparatus generates an image based on the image embedding, wherein the image includes an element described by the text prompt.

公开(公告)号：US12118693B2

公开(公告)日：2024-10-15

申请号：US17950331

申请日：2022-09-22

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Alok Shankarlal Shukla ,  Manoj Kumar ,  Saketh Sharma ,  Woojhon Choi ,  Wonjoon Do ,  Jaesung Choi

IPC: G06T5/50 ,  G06T5/73 ,  G06T5/80 ,  G06T7/10 ,  G06T7/70 ,  H04N5/265 ,  H04N23/53 ,  H04N23/71 ,  H04N23/72 ,  H04N23/741

CPC classification number: G06T5/50 ,  G06T5/73 ,  G06T5/80 ,  G06T7/10 ,  G06T7/70 ,  H04N5/265 ,  H04N23/53 ,  H04N23/71 ,  H04N23/72 ,  H04N23/741 ,  G06T2207/10024 ,  G06T2207/10144 ,  G06T2207/20208 ,  G06T2207/20221

Abstract: An electronic device includes a UDC and a UDC controller configured to determine an optimal number of frames required to be captured for a scene to compensate at least one parameter to optimize an output media using the UDC, obtain a multi-frame fusion media by performing at least one multi-frame fusion on the determined optimal number of frames, perform a light source spread correction on the multi-frame fusion media, and optimize the output media based on the light source spread correction on the multi-frame fusion media.

公开(公告)号：US20240331104A1

公开(公告)日：2024-10-03

申请号：US18598980

申请日：2024-03-07

Applicant: Sukhmeet Singh

Inventor： Sukhmeet Singh

IPC: G06T5/60 ,  G06T5/50 ,  G06T5/73 ,  G06T5/92 ,  G06T11/00 ,  G06V10/56 ,  G06V10/82 ,  G06V20/52

CPC classification number: G06T5/60 ,  G06T5/50 ,  G06T5/73 ,  G06T5/92 ,  G06T11/001 ,  G06V10/56 ,  G06V10/82 ,  G06V20/52 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20084 ,  G06T2207/20212 ,  G06T2210/52

Abstract: Systems and methods are disclosed for image enhancement and de-hazing video. Various embodiments comprise a convolutional neural network having a U-net architecture with pairs of encoder and decoder convolutional blocks. In one or more embodiments the CNN is configured with a layer-to-layer skip-connection between layers of each pair of convolutional blocks to transfer a feature map from an encoder portion to a decoder portion. Various embodiments further comprise a processor and program instructions executable by the processor to cause the processor to receive an input image and generate one or more data sets of images corresponding to channels that define one or more color spaces. Various embodiments comprise processing each of the images into a plurality of processed outputs corresponding to color space channels and generating a dehazed image by convoluting a concatenation of the plurality of processed outputs.