Samsung Electronics Co., Ltd.

Yonsei University

Seunghoon Jee

Moon Gi Kang

Minsub Kim

Sang Yoon Lee

Sangyoon Lee

Paul Oh

Suji Kim

Min Sub Kim

Soonyoung Hong

Dongwon Jang

Soon Young Hong

A neural codec includes a first simulated predictor for predicting a first block corresponding to a target block within a current frame, wherein the first block is predicted in accordance with the target block of the to-be-predicted current frame and pixels of neighbor blocks adjacent to the target block being input to the first simulated predictor, a second simulated predictor for predicting a second block corresponding to a target block using a reference block of a frame determined based on a prediction mode, wherein the second block is predicted in accordance with the reference block of a reference frame adjacent to the current frame and the target block being input to the second simulated predictor, and a selection network configured to select, based on the prediction mode, one of the first block and the second block as a predicted block.

Method and apparatus with neural codec

A method and apparatus with image processing are disclosed. The method includes determining a real part image, an imaginary part image, and an offset image based on input images that are dependent on infrared rays of different phases, removing noise from each of the real part image and the imaginary part image using the offset image as a noise removal guide, and generating a depth image based on an improved real part image and an improved imaginary part image corresponding to respective results of the removing.

Method and apparatus with image processing

A method with three-dimensional (3D) modeling of a wearer of a wearable device includes generating a feature map for each of a plurality of images of the wearer obtained from a plurality of imaging devices provided in the wearable device, obtaining joint keypoint information corresponding to joint positions of the wearer and initial shape coefficient information associated with a shape of the wearer based on the feature map for each of the images, determining a target 3D joint angle for 3D modeling of the wearer based on the joint keypoint information and the initial shape coefficient information, determining target shape coefficient information for 3D modeling of the wearer based on the joint keypoint information and the initial shape coefficient information, and obtaining a 3D mesh of the wearer based on the target 3D joint angle and the target shape coefficient information.

Method and apparatus with 3D modeling of human body

A human body estimating method includes: receiving an image frame including a two-dimensional (2D) human body from a camera; determining a 2D appearance parameter of the 2D human body by analyzing the image frame; determining a three-dimensional (3D) appearance parameter of the 2D human body based on the 2D appearance parameter, a camera parameter of the camera, a 3D space parameter of the 2D human body; and estimating a 3D human body corresponding to the 2D human body based on the 3D space parameter and the 3D appearance parameter.

Method and apparatus with human body estimation

An image processing method includes: determining a source transmission map based on a dark channel map of an input image; determining transformed transmission maps by applying different filters to the determined source transmission map; generating haze-free images by removing haze from the input image based respectively on the determined transformed transmission maps; and generating an output image by blending the generated haze-free images.

Growing community of inventors

Seoul, South Korea

Seunghoon Jee