Resumes
Resumes
Wenbo Li Phones & Addresses
-
Saratoga, CA
-
Sunnyvale, CA
-
Milpitas, CA
-
Newark, CA
-
San Jose, CA
Publications
Us Patents
Image Super-Resolution With Reference Images From One Or More Cameras
View pageUS Patent:
20220368829, Nov 17, 2022
Filed:
Oct 4, 2021
Appl. No.:
17/493268
Inventors:
- Suwon-si, KR
Wenbo LI - Santa Clara CA, US
Hongxia JIN - San Jose CA, US
Wenbo LI - Santa Clara CA, US
Hongxia JIN - San Jose CA, US
Assignee:
SAMSUNG ELECTRONICS CO., LTD. - Suwon-si
International Classification:
H04N 5/232
G06T 5/00
G06T 5/50
G06T 5/20
G06T 5/00
G06T 5/50
G06T 5/20
Abstract:
A super resolution is produced using multiple reference images. Reference images are upsampled and blurred as needed for comparison between images of different resolution. Patches in blurred images are searched to find those patches which can be assembled into vectors for improving feature content over multiple resolution levels. The searches are based on similarity maps. The assembled vectors are concatenated with one or more other vectors, up-converted and then passed through convolutional layers to obtain new feature vectors. A final feature vector is passed through a convolutional layer to obtain the super resolution image.
Visual Object Instance Segmentation Using Foreground-Specialized Model Imitation
View pageUS Patent:
20210407090, Dec 30, 2021
Filed:
Jun 24, 2020
Appl. No.:
16/946504
Inventors:
- Suwon-si, KR
Wenbo Li - Santa Clara CA, US
Hongxia Jin - San Jose CA, US
Wenbo Li - Santa Clara CA, US
Hongxia Jin - San Jose CA, US
International Classification:
G06T 7/10
G06N 3/04
G06K 9/62
G06N 3/04
G06K 9/62
Abstract:
A method includes training, using at least one processor, a specialized teacher model to perform visual object instance segmentation in order to segment and classify objects in first training images. The first training images contain foreground objects without backgrounds. The method also includes training, using the at least one processor, a student model to perform visual object instance segmentation in order to segment and classify objects in second training images. The second training images contain the foreground objects and the backgrounds. Training the student model includes using selected outputs of the specialized teacher model. The method further includes deploying the trained student model to perform visual object instance segmentation in an external device.