-
公开(公告)号:US20250078201A1
公开(公告)日:2025-03-06
申请号:US18646032
申请日:2024-04-25
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Jason J. YU , Marcus A. Brubaker , Konstantinos G. Derpanis , Aleksai Levinshtein
IPC: G06T3/4007 , G06T3/4038 , G06T3/4046
Abstract: Disclosed are an electronic device and a method including obtaining a plurality of images using an image sensor of the electronic device, obtaining synthetic training data for pre-training a burst processing network, performing implicit interpolation on the obtained plurality of images based on the pre-trained burst processing network, combining the plurality of images into a target image based on the implicit interpolation, and outputting the target image to a display of the electronic device.
-
公开(公告)号:US20240311968A1
公开(公告)日:2024-09-19
申请号:US18387964
申请日:2023-11-08
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Shayan SHEKARFOROUSH , Amanpreet Singh Walia , Aleksai Levinshtein , Konstantinos G. Derpanis , Marcus A. Brubaker
CPC classification number: G06T5/50 , G06T5/70 , G06T5/73 , G06T7/248 , H04N23/71 , H04N23/72 , H04N23/73 , H04N23/76 , G06T2207/10016 , G06T2207/10024 , G06T2207/10144 , G06T2207/20081 , G06T2207/20084 , G06T2207/20201 , G06T2207/20221 , G06T2207/30241
Abstract: The present disclosure provides methods, apparatuses, and computer-readable mediums for image processing, to be performed by an image processing framework, that include simultaneously capturing a long exposure image and a burst of short exposure images, recovering motion information from the burst of short exposure images, performing motion-aware deblurring of the long exposure image based on the motion information, denoising the burst of short exposure images based on the motion information, and fusing first features of a deblurred long exposure image and second features of a denoised image to obtain a final deblurred and denoised image.
-
公开(公告)号:US20250078362A1
公开(公告)日:2025-03-06
申请号:US18816534
申请日:2024-08-27
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Ashkan MIRZAEI , Tristan Ty Aumentado-Armstrong , Marcus A. Brubaker , Igor Gilitschenski , Aleksai Levinshtein , Konstantinos G. Derpanis
Abstract: A method for editing a local area of a target image using a diffusion model, includes: receiving an input image; receiving a text instruction to edit the input image; generating a relevance map based on the diffusion model and the text instruction; generating a rendered image by performing a relevance guided image editing method on the input image, based on the generated relevance map; and providing, to the user, the generated rendered image.
-
-