Yonsei University

Electronics and Telecommunications Research Institute

Korea Electronics Technology Institute

Kwang Hoon Sohn

Suk Hee Cho

Soo In Lee

Kug Jin Yun

Yong Kim

Dae Hee Kim

Chung Hyun Ahn

Dong Hyun Kim

Seok Min Lee

Ho Cheon Wey

Byeong Ho Choi

Je Woo Kim

Sun Ok Kim

Hyeok Koo Jung

Sung Hun Joung

Jeong Eun Lim

Jung Dong Seo

The present disclosure provides an apparatus for cylindrical convolutional neural network operation, and an apparatus and method for object recognition and viewpoint estimation using the same. The present disclosure uses a cylindrical convolutional network to recognize objects in the image and to determine the viewpoint, which cylindrical convolutional network performs a convolution operation while sliding the input image in the direction of rotation of the cylindrical kernel and extracts a plurality of view-specific feature vectors according to angular unit intervals, to identify and recognize objects, as well as to determine the viewpoint from which the objects were photographed.

Apparatus for performing cylindrical convolutional neural network operation and apparatus and method for object recognition and viewpoint estimation using the same

A method and device for transforming 2D images into 3D are disclosed. The disclosed device includes a dictionary storage unit configured to store a word-depth gradient dictionary; a color patch obtainer unit configured to obtain color patches from an input image; a matching word search unit configured to transform each of the color patches obtained by the color patch obtainer unit into a SIFT descriptor form and search for words closest to the SIFT descriptors of the obtained color patches from among the words of the word-depth gradient dictionary; a matching depth gradient obtainer unit configured to obtain depth gradient information of the words matching the obtained color patches from the word-depth gradient dictionary; and a depth map generation unit configured to compute a depth from the obtained matching depth gradient for each of the obtained color patches and generate a depth map.

Method and device for transforming 2D image into 3D

Provided is an image processing apparatus, method and computer-readable medium. When encoding a multi-view color and depth video, a motion vector calculator of the image processing apparatus may calculate a block motion vector with respect to a first viewpoint color image. A motion vector borrowing unit may borrow, as a block motion vector with respect to a second viewpoint color image, a block motion vector with respect to the first viewpoint color image based on a disparity calculated from a depth video.

Multi-view image processing apparatus, method and computer-readable medium

Provided is a method and apparatus for encoding and decoding multi-view video data. The encoding method includes: decomposing each view image of the multi-view video into an overlapped region and a non-overlapped region, the overlapped region being overlapped with other view image and the non-overlapped region not being overlapped with other view image; generating a stitched image by combining the non-overlapped region of each view image and a middle view image; encoding the stitched image using a first encoding algorithm; and encoding the overlapped region of each view image, using a second encoding algorithm. Further, the decomposing step includes the steps of estimating disparity information for each view image, based on a predetermined view image; and decomposing each view image into said overlapped region and said non-overlapped region using the estimated disparity information.

Method and apparatus for encoding and decoding multi-view video using image stitching

A disparity prediction stage and a motion prediction stage predict a disparity vector and a motion vector by extending a MPEG-2 structure into a view axis and using spatial/temporal correlation. A disparity/motion compensation stage compensates an image reconstructed by the disparity prediction stage and the motion prediction stage by using a sub-pixel compensation method. A residual image encoding stage performs an encoding to provide a better visual quality and a three-dimensional effect of an original image and the reconstructed image. A bit rate control stage controls a bit rate for assigning an effective amount of bit to each frame on the reconstructed image according to a bit rate. An entropy encoding stage generates a bit stream on multi-view video source data according to the bit rate.

Apparatus for encoding a multi-view moving picture

Growing community of inventors

Seoul, South Korea

Kwang Hoon Sohn