Samsung electronics co., ltd. (20250063136). GENERATIVE AI-BASED VIDEO ASPECT RATIO ENHANCEMENT
GENERATIVE AI-BASED VIDEO ASPECT RATIO ENHANCEMENT
Organization Name
Inventor(s)
Tomasz Jan Palczewski of Danville CA (US)
Anirudh Rao of San Jose CA (US)
Hong-Hoe Kim of Aliso Viejo CA (US)
GENERATIVE AI-BASED VIDEO ASPECT RATIO ENHANCEMENT
This abstract first appeared for US patent application 20250063136 titled 'GENERATIVE AI-BASED VIDEO ASPECT RATIO ENHANCEMENT
Original Abstract Submitted
a method includes obtaining, using at least one processing device of an electronic device, a video including multiple scenes at a first aspect ratio. the method also includes performing, using the at least one processing device, backward optical flow estimation and forward optical flow estimation for each of the multiple scenes to select an image frame having a largest missing area. the method further includes performing, using the at least one processing device, outpainting on the image frame having the largest missing area to generate a first outpainted image frame at a second aspect ratio different from the first aspect ratio. in addition, the method includes performing, using the at least one processing device, backward optical flow estimation and forward optical flow estimation using the first outpainted image frame to generate additional outpainted image frames in the multiple scenes at the second aspect ratio.
