Method and apparatus for two-dimensional to three-dimensional image conversion
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06T-015/08
H04N-013/02
G06T-007/00
출원번호
US-0035984
(2013-09-25)
등록번호
US-9462257
(2016-10-04)
발명자
/ 주소
Zurek, Robert A.
Dickinson, Timothy
출원인 / 주소
Google Technology Holdings LLC
대리인 / 주소
Troutman Sanders LLP
인용정보
피인용 횟수 :
2인용 특허 :
6
초록▼
A method and apparatus provide two-dimensional to three-dimensional image conversion. The apparatus can include an input configured to receive a first image. The apparatus can include a controller configured to segment the first image into a plurality of regions, configured to perform a Fast Fourier
A method and apparatus provide two-dimensional to three-dimensional image conversion. The apparatus can include an input configured to receive a first image. The apparatus can include a controller configured to segment the first image into a plurality of regions, configured to perform a Fast Fourier Transform on at least one of the regions, and configured to determine a relative horizontal displacement distance between a first frame and a second frame of at least one region based on performing the Fast Fourier Transform.
대표청구항▼
1. A method comprising: receiving a first image;segmenting the first image into a plurality of regions, each region of the first image comprising a frame;performing, on a first region of the plurality of regions, the first region comprising a first frame, a Fast Fourier Transform that comprises summ
1. A method comprising: receiving a first image;segmenting the first image into a plurality of regions, each region of the first image comprising a frame;performing, on a first region of the plurality of regions, the first region comprising a first frame, a Fast Fourier Transform that comprises summing high frequency coefficients of averaged Fast Fourier Transform spectra of the first region to provide a summed high frequency coefficient of the first region;determining, from the summed high frequency coefficient of the first region and a summed high frequency coefficient of a second region, a largest summed high frequency coefficient;using a ratio of the largest summed high frequency coefficient to the summed high frequency coefficient of the first region, determining a horizontal displacement distance for the first region;generating a second image, the second image also comprising the plurality of regions, wherein a first region of the second image corresponds to the first region of the first image, and wherein the first region of the second image comprises a second frame, the second frame being a copy of the first frame displaced by the determined horizontal shift; andcreating a stereoscopic image by combining the first frame and the second frame. 2. The method according to claim 1, wherein the frames of each region of the first image are original frames the plurality of regions of the first image. 3. The method according to claim 1, further comprising: performing a Fast Fourier Transform on a first portion of the first region;performing a Fast Fourier Transform on a second portion of the first region; andascertaining a tilt of the first region from the first portion to the second portion. 4. The method according to claim 3, wherein the tilt of the first region is a depth relative to a plane parallel to the height and width of the first image. 5. The method according to claim 3, further comprising: adjusting a perceived tilt of the first region based on the ascertained tilt. 6. The method according to claim 1, further comprising: receiving a user input to adjust a depth of an adjustment region; andadjusting a depth ranking of the adjustment region based on the user input. 7. The method according to claim 1, wherein the horizontal displacement distance for the first region is a function of a depth of the first region determined from the Fast Fourier Transform process. 8. An apparatus comprising: an input for receiving images;a controller; anda non-transitory storage medium storing instructions that, when executed by the controller, cause the apparatus to: receive a first image;segment the first image into a plurality of regions, each region of the first image comprising a frame;perform, on a first region of the plurality of regions, the first region comprising a first frame, a Fast Fourier Transform that comprises summing high frequency coefficients of averaged Fast Fourier Transform spectra of the first region to provide a summed high frequency coefficient of the first region;determine, from the summed high frequency coefficient of the first region and a summed high frequency coefficient of a second region, a largest summed high frequency coefficient;use an a ratio of the largest summed high frequency coefficient to the summed high frequency coefficient of the first region to determine a horizontal displacement distance for the first region;generate a second image, the second image also comprising the plurality of regions, wherein a first region of the second image corresponds to the first region of the first image, and wherein the first region of the second image comprises a second frame, the second frame being a copy of the first frame displaced by the determined horizontal shift; andcreate a stereoscopic image by combining the first frame and the second frame. 9. The apparatus according to claim 8, wherein the frames of each region of the first image are original frames the plurality of regions of the first image. 10. The apparatus according to claim 8, wherein the non-transitory storage medium further stores instructions that, when executed by the processor, cause the apparatus to perform a Fast Fourier Transform on a first portion of the first region;perform a Fast Fourier Transform on a second portion of the first region; andascertain a tilt of the first region from the first portion to the second portion. 11. The apparatus according to claim 10, wherein the tilt of the first region is a depth relative to a plane parallel to the height and width of the first image. 12. The apparatus according to claim 10, wherein the non-transitory storage medium further stores instructions that, when executed by the processor, cause the apparatus to adjust a perceived tilt of the first region based on the ascertained tilt. 13. The apparatus according to claim 8, wherein the non-transitory storage medium further stores instructions that, when executed by the processor, cause the apparatus to: receive a user input to adjust a depth of an adjustment region; andadjust a depth ranking of the adjustment region based on the user input. 14. The apparatus according to claim 8, wherein the horizontal displacement distance for the first region is a function of a depth of the first region determined from the Fast Fourier Transform process.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (6)
Chen, Liang-Gee; Cheng, Chao-Chung; Li, Chung-Te; Huang, Ling-Hsiu, 3D depth generation by local blurriness estimation.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.