Samsung Electronics Co., Ltd.

Yonsei University

Wooshik Kim

Daesung Cho

Dmitri Birinov

Hyun Mun Kim

Sangjo Lee

Sunghoon Hong

Qiang Wang

Chao Zhang

Seungwoo Lee

Weiming Li

Woochul Kim

Yang Liu

Hao Wang

Lin Ma

Doohyun Kim

Shihwa Lee

Yueying Kao

Jinhyung Park

Jiyeon Kim

Keechang Lee

Daehee Kim

Hwiryong Jung

Moon Gi Kang

Hyewon Moon

Min Sub Kim

JongSeon Kim

Seung Hoon Jee

Shinwa Lee

Bomyun Kim

An electronic device for estimating object information and generating a virtual object and a method of operating the electronic device are disclosed. The method includes obtaining an image, obtaining a class feature, a pose feature, and a relationship feature of an object included in the image, correcting each of the class feature, the pose feature, and the relationship feature using any combination of any two or more of the class feature, the pose feature, and the relationship feature of the object, and obtaining class information, pose information, and relationship information of the object based on the corrected class feature, the corrected pose feature, and the corrected relationship feature, respectively.

Method and apparatus with object information estimation and virtual object generation

An image processing apparatus and method are provided. The image processing apparatus acquires a target image including a depth image of a scene, determines three-dimensional (3D) point cloud data corresponding to the depth image based on the depth image, and extracts an object included in the scene to acquire an object extraction result based on the 3D point cloud data.

Image processing apparatus and method

A method of displaying a three-dimensional (3D) object includes acquiring a driving image from a single camera, classifying line marks including a road surface into one or more groups based on a change in a curvature of a line of the road surface, estimating a pitch angle corresponding to an angle of inclination between the road surface and the single camera for each of the one or more groups, generating 3D information of the road surface, and displaying an 3D object visually overlaid on the road surface based on the 3D information of the road surface.

Method and apparatus with three-dimensional object display

An image processing method acquires an image, restores a saturated region in which a pixel in the image has a first reference value based on a first illuminance component of the image, enhances a dark region in which a value of a pixel in the image is less than a second reference value based on the restored saturated region and the first illuminance component, and outputs a dark region-enhanced image.

Image processing method and apparatus

An image decoding apparatus is provided. The image decoding apparatus includes a processor which obtains information about a color representation from a bitstream, obtains a residue, which corresponds to a difference between a current image and a predicted image of the current image, from the bitstream, and reconstructs the current image by using the residue and the predicted image, based on the information about the color representation.

Moving picture coding/decoding method and apparatus

An image decoding method is provided. The image decoding method includes obtaining information about a color representation from a bitstream, entropy decoding a residue, which corresponds to a difference between a current image and a predicted image of the current image, and reconstructing the current image by using the entropy decoded residue and the predicted image, based on the information about the color representation.

A moving picture coding/decoding method and apparatus with improved coding efficiency. A moving picture coding method includes selecting a color space from among a plurality of color spaces, selecting a prediction mode to be commonly applied to all the color components constituting the selected color space, generating first residual data corresponding to differences between a current picture and a predicted picture for each of the color components according to the selected prediction mode, generating second residual data corresponding to differences between the first residual data, and coding the second residual data.

A method, medium, and system encoding/decoding video data using a binary arithmetic coding adaptive to a compression bit rate of the video data. The system may include a bitrate adaptation unit determining a maximum length of a prefix using a compression bitrate of the video data, a binarization unit dividing the video data into a prefix and a suffix according to the determined maximum length of the prefix and binarizing the video data, and an arithmetic encoding unit performing an arithmetic encoding on the binarized video data. The video data may be encoded/decoded using binary arithmetic encoding/decoding by determining the maximum length of the prefix, an order of an exponential Golomb code, and the number of contexts based on the compression bitrate. Accordingly, it is possible to obtain high encoding efficiency regardless of a range of the desired compression bitrate.

Method, medium, and system encoding/decoding video data using bitrate adaptive binary arithmetic coding

An apparatus and method for coding and decoding an image are provided. The apparatus for coding the image includes a spatio-temporal information prediction/compensation unit, a recovered image processor, a residue generator, a quantizer, and an entropy encoder. The spatio-temporal information prediction/compensation unit generates a predicted image by predicting and compensating spatio-temporal information including at least one of temporal prediction information from a current image and a recovered previous image, and spatial prediction information from a recovered current image. The recovered image processor performs a spatio-temporal noise removal process on the recovered current image using the spatio-temporal information, and stores the resulting noise-removed image. The residue generator generates a residue image obtained by subtracting the predicted image from the input image, and the quantizer outputs quantized coefficients by quantizing the residue image. The entropy encoder generates a bit stream by entropy coding the quantized coefficients.

Apparatus and method for coding and decoding image

A method, medium, and apparatus controlling a bit rate in image data encoding. The method for controlling a bit rate in image data encoding includes setting a reference bit amount for encoding a block group composed of a predetermined number of blocks created by dividing image data of a frame, encoding pixel values of the blocks according to a bit depth used to quantize the pixel values of the blocks, checking whether encoding of the frame is completed, and comparing a group bit amount indicating the amount of encoded bits of the block group with the set reference bit amount to adjust the bit depth if encoding of the unit frame is not completed and accordingly repeating the setting of the reference bit amount, encoding pixel values of the blocks, and checking whether encoding of the frame is completed.

Method, medium, and apparatus controlling bit rate in image data encoding

A method of encoding image data, and an apparatus to perform the method, the method including repeating a process of dividing a block into sub-blocks based on an average value of pixels of the sub-blocks; creating map information of the sub-blocks; determining a mode for generating bit streams according to a number of the sub-blocks; and generating bit streams of the determined mode, map information, and representative pixel values of the block or the sub-blocks.

Method and apparatus for encoding image data including generation of bit streams

An apparatus and a method for encoding and/or decoding an image containing a gray alpha channel image. The apparatus for encoding an image includes a block data reception unit receiving image data of a block currently being input to the apparatus and classifies the current block either as a foreground image portion or as a background image portion according to values of gray alpha components in the current block; a foreground image encoding unit sequentially encoding the gray alpha components and brightness and hue components of the current block if the current block is classified as the foreground image portion; and a background image encoding unit encoding the gray alpha components of the current block if the current block is classified as the background image portion. The apparatus for decoding an image includes a bitstream interpretation unit interpreting the bitstream in units of predetermined blocks and classifies a current block obtained as one of the interpretation results either as a foreground image portion or as a background image portion; a foreground image decoding unit generating a restored gray alpha channel image and a restored brightness and hue image by sequentially decoding gray alpha components and brightness and hue components of the current block if the current block is classified as the foreground image portion; and a background image decoding unit generating a restored gray alpha channel image by decoding the gray alpha components of the current block if the current block is classified as the background image portion.

Growing community of inventors

Yongin-si, South Korea

Wooshik Kim