公开(公告)号：US20240394830A1

公开(公告)日：2024-11-28

申请号：US18433133

申请日：2024-02-05

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sajid Sadi ,  Varun Menon ,  Siddarth Ravichandran ,  Chuhua Wang ,  Hyun Jae Kang ,  Rahul Lokesh ,  Vignesh Gokul

IPC: G06T3/18 ,  G06T11/60 ,  G06V10/25

Abstract: Synthesizing high-resolution input for rendering a digital human includes generating, with a generative artificial intelligence (AI) model, a distorted image of the digital human by enhancing a region of interest (ROI) within the distorted image relative to other regions of the distorted image. The generative AI model is previously trained against a distorted control image generated using a distortion function to distort a control image used to guide image generation by the generative AI model. The distorted control image is generated by reconfiguring and augmenting pixels of the control image. An undistorted image of the digital human is generated using a reverse distortion function to reverse distortion of the distorted image.

公开(公告)号：US20240394855A1

公开(公告)日：2024-11-28

申请号：US18433157

申请日：2024-02-05

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sajid Sadi ,  Varun Menon ,  Siddarth Ravichandran ,  Hyun Jae Kang ,  Anil Unnikrishnan ,  Anthony Sylvain Jean-Yves Liot

IPC: G06T5/80 ,  G06T13/40 ,  G06V10/25

Abstract: Synthesizing high-resolution data includes distorting, with a distortion function, a region of interest (ROI) within an input of inferential data. The distorting generates distortion data within which the ROI is enhanced relative to other regions of the distortion data. A generative artificial intelligence (AI) model generates synthetic data in response to input of the distortion data. The generative AI model is trained against a distorted ground truth generated using the distortion function to distort one or more regions of interest ROI within source data used to guide the generative AI model in generating the synthetic data.

公开(公告)号：US20240354996A1

公开(公告)日：2024-10-24

申请号：US18428487

申请日：2024-01-31

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Varun Menon ,  Siddarth Ravichandran ,  Ankur Gupta ,  Hyun Jae Kang ,  Sajid Sadi

IPC: G06T9/00 ,  G06V10/764

CPC classification number: G06T9/00 ,  G06V10/764

Abstract: Autoregressive content rendering for temporally coherent video generation includes generating, by an autoencoder, a plurality of predicted images. The plurality of predicted images is fed back to the autoencoder network. The plurality of predicted images may be encoded by the autoencoder network to generate a plurality of encoded predicted images. The autoencoder network encodes a plurality of keypoint images to generate a plurality of encoded keypoint images. One or more predicted images of the plurality of predicted images are generated by the autoencoder network by decoding a selected encoded keypoint image of the plurality of encoded keypoint images with an encoded predicted image of the plurality of encoded predicted images of a prior iteration of the autoencoder network.