# US 2014/0152658 A1 · Image processing apparatus and method for generating 3d image thereof > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2014/0152658 A1 - Document ID: US20140152658A1 - Status: Published application - Kind: A1 - Application number: 14/097,322 - Filed: 2013-12-05 - Published: 2014-06-05 - Earliest claimed: 2012-12-05 - Assignees: Samsung Electronics Co., Ltd. - Applicants: Samsung Electronics Co., Ltd. - Inventors: Won-seok AHN; Beom-joon KIM; Jin-woo JEONG - Web page: https://patentgrep.com/patent/US20140152658A1 ## CPC - G06T 15/00: Three-dimensional [3D] image rendering - H04N 13/122: Improving the three-dimensional [3D] impression of stereoscopic images by modifying image signal contents, e.g. by filtering or adding monoscopic depth cues (H04N13/128 takes precedence) - H04N 13/128: Adjusting depth or disparity - H04N 13/133: Equalising the characteristics of different image components, e.g. their average brightness or colour balance - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract A method including acquiring a source image and depth information of the source image, determining, using depth information, an overlapping region in which some pixels of a source image are shifted and a plurality of pixels overlap, calculating a weight for the overlapping region with a processor, using distance information with respect to a foreground region of the source image and a background region of the source image, generating, using the depth information and the overlapping region, a foreground-depth image in which the foreground region is extended and a background-depth image in which the background region is extended, generating a foreground image using the source image and the foreground-depth image, generating a background image using the source and the background-depth image, and generating, using the weight from the overlapping region, at least one of a left-eye image and a right-eye image by synthesizing the foreground image and the background image. ## Claims ### Claim 1 A method for generating a three-dimensional (3D) image, the method comprising: acquiring a source image and depth information of the source image; determining, using the depth information, an overlapping region in which some pixels of the source image are shifted and a plurality of pixels overlap; calculating a weight for the overlapping region with a processor, using distance information with respect to a foreground region of the source image and a background region of the source image; generating, using the depth information and the overlapping region, a foreground-depth image in which the foreground region is extended and a background-depth image in which the background region is extended; generating a foreground image using the source image and the foreground-depth image; generating a background image using the source image and the background-depth image; and generating, using the weight from the overlapping region, at least one of a left-eye image and a right-eye image with respect to the source image by synthesizing the foreground image and the background image. ### Claim 2 (depends on 1) The method as claimed in claim 1, wherein the calculating a weight includes calculating the weight so that among the pixels of the overlapping region, pixels closer to the foreground region have higher weights than pixels closer to the background region. ### Claim 3 (depends on 2) The method as claimed in claim 2, wherein the generating one of a left-eye image and a right-eye image with respect to the source image includes adjusting a pixel value of a region having a first weight among the overlapping region based on a pixel value of the foreground image and adjusting a pixel value of a region having a second weight among the overlapping region based on a pixel value of the background image, and wherein the first weight is higher than the second weight. ### Claim 4 (depends on 1) The method as claimed in claim 1, wherein the determining further includes determining a hole region generated by shifting some of the pixels of the source image according to the depth information. ### Claim 5 (depends on 4) The method as claimed in claim 4, further comprising, in response to determining the overlapping region and the hole region, removing noise from the overlapping region and the hole region. ### Claim 6 (depends on 5) The method as claimed in claim 5, further comprising, in response to removing the noise from the overlapping region and the hole region, performing pre-processing on the depth information based on the noise-removed overlapping region and hole region. ### Claim 7 (depends on 4) The method as claimed in claim 4, wherein the foreground-depth image in which the foreground region is extended and the background-depth image in which the background region is extended are generated based on the depth information and at least one of the overlapping region and the hole region. ### Claim 8 (depends on 1) The method as claimed in claim 1, further comprising, in response to generating the foreground-depth image in which the foreground region is extended and the background-depth image in which the background region is extended, performing post-processing on the foreground-depth image and the background-depth image. ### Claim 9 (depends on 1) The method as claimed in claim 1, wherein the source image is a two-dimensional (2D) image. ### Claim 10 An image processing apparatus which generates a three-dimensional (3D) image, the image processing apparatus comprising: a receiver configured to receive a source image and depth information of the source image; a region determination unit configured to determine, using the depth information, an overlapping region in which some pixels of the source image are shifted and a plurality of pixels overlap; a weighting unit configured to calculate, using distance information with respect to a foreground region of the source image and a background region of the source image, a weight of the determined overlapping region; a depth image generator configured to generate, using the depth information and the overlapping region, a foreground-depth image in which the foreground region is extended and a background-depth image in which the background region is extended; and a 3D image generator configured to: generate a foreground image using the source image and the foreground-depth image; generate a background image using the source image and the background-depth image; synthesize, using the calculated weight, the foreground image and the background image; and generate at least one of a left-eye image and a right-eye image with respect to the source image. ### Claim 11 (depends on 10) The image processing apparatus as claimed in claim 10, wherein the weighting unit is configured to calculate the weight so that among the pixels of the overlapping region, pixels closer to the foreground region have higher weights than pixels closer to the background region. ### Claim 12 (depends on 11) The image processing apparatus as claimed in claim 11, wherein the 3D image generator is further configured to: adjust, using a pixel value of the foreground image, a pixel value of a region having a first weight among the overlapping region; and adjust, using a pixel value of the background image, a pixel value of a region having a second weight among the overlapping region, and wherein the first weight is higher than the second weight. ### Claim 13 (depends on 10) The image processing apparatus as claimed in claim 10, wherein the region determination unit is further configured to determine a hole region generated by shifting some of the pixels of the source image using the depth information. ### Claim 14 (depends on 13) The image processing apparatus as claimed in claim 13, further comprising a noise processing unit configured to remove noise from the overlapping region and the hole region. ### Claim 15 (depends on 14) The image processing apparatus as claimed in claim 14, further comprising a pre-processing unit configured to perform pre-processing on the depth information using the noise-removed overlapping region and the noise-removed hole region. ### Claim 16 (depends on 13) The image processing apparatus as claimed in claim 13, wherein the 3D image generator generates the foreground-depth image in which the foreground region is extended and the background-depth image in which the background region is extended using the depth information and at least one of the overlapping region and the hole region. ### Claim 17 (depends on 10) The image processing apparatus as claimed in claim 10, further comprising a post-processing unit configured to perform post-processing on the foreground-depth image and the background-depth image, wherein, in response to the foreground-depth image in which the foreground region is extended and the background-depth image in which the background region is extended being generated, the post-processing unit performs the post-processing on the foreground-depth image and the background-depth image. ### Claim 18 (depends on 10) The image processing apparatus as claimed in claim 10, wherein the source image is a two-dimensional (2D) image. ### Claim 19 An image processing apparatus which generates a three-dimensional (3D) image, the image processing apparatus comprising: a receiver configured to receive a source image and depth information associated with the source image, the source image including a foreground region in which a foreground image is displayed and a background region in which a background image is displayed, the depth information indicating the foreground region and the background region; and a controller configured to generate the 3D image by performing a pixel shifting operation in which pixels of one of the foreground region and the background region are shifted by a predetermined number of pixels without shifting pixels of the other region, to determine, based on the pixel shifting operation, at least one of an overlapping region in which pixels overlap and a hole region in which there are no pixels, and to generate a left-eye image and a right-eye image using the foreground image, the background image, and at least one of the overlapping region and the hole region.