Generation of three-dimensional imagery from a two-dimensional image using a depth map
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06T-017/20
G02B-027/01
H04N-013/106
H04N-013/111
H04N-013/25
H04N-013/275
H04N-013/344
G06T-009/00
출원번호
US-0650671
(2017-07-14)
등록번호
US-10096157
(2018-10-09)
발명자
/ 주소
Herman, Brad Kenneth
출원인 / 주소
DreamWorks Animation L.L.C.
대리인 / 주소
Dentons US LLP
인용정보
피인용 횟수 :
0인용 특허 :
4
초록▼
A method for generating stereoscopic images includes obtaining image data comprising a plurality of sample points. A direction, a color value, and a depth value are associated with each sample point. The directions and depth values are relative to a common origin. A mesh is generated by displacing t
A method for generating stereoscopic images includes obtaining image data comprising a plurality of sample points. A direction, a color value, and a depth value are associated with each sample point. The directions and depth values are relative to a common origin. A mesh is generated by displacing the sample points from the origin. The sample points are displaced in the associated directions by distances representative of the corresponding depth values. The image data is mapped to the mesh such that the color values associated with the sample points are mapped to the mesh at the corresponding directions. A first image of the mesh is generated from a first perspective, and a second image of the mesh is generated from a second perspective. The first and second images of the mesh may be caused to be displayed to provide an illusion of depth.
대표청구항▼
1. A computer-implemented method for generating stereoscopic images, the method comprising: obtaining image data comprising directions and depth values associated with pixels in an image;generating a first vertex based on the directions and depth values associated with the pixels of the image, where
1. A computer-implemented method for generating stereoscopic images, the method comprising: obtaining image data comprising directions and depth values associated with pixels in an image;generating a first vertex based on the directions and depth values associated with the pixels of the image, wherein a direction and a depth value are associated with the first vertex,generating a second vertex based on the directions and depth values associated with the pixels of the image, wherein a direction and a depth value are associated with the second vertex,wherein the directions and depth values associated with the first vertex and the second vertex are relative to an origin, andwherein the origin is common to both the first vertex and the second vertex;generating a mesh, wherein generating the mesh comprises: displacing the first vertex from the origin in a direction associated with the first vertex by a distance representative of the depth value associated with the first vertex; anddisplacing the second vertex from the origin in a direction associated with the second vertex by a distance representative of the depth value associated with the second vertex;generating a first image of the mesh from a first perspective; andgenerating a second image of the mesh from a second perspective. 2. The computer-implemented method of claim 1, wherein generating a first vertex comprises: interpolating the direction and depth value of the first vertex based on the directions and depth values of the pixels surrounding the first vertex. 3. The computer-implemented method of claim 1, wherein generating a mesh comprises: displacing the first vertex in a direction defined by coordinates in the horizontal direction and vertical direction. 4. The computer-implemented method of claim 1, wherein the first and second perspectives are of locations near the origin. 5. The computer-implemented method of claim 4, wherein the first and second perspectives are of each of two points adjacent to and approximately equal distance from the origin. 6. The computer-implemented method of claim 1, wherein the image is of a scene from the perspective of a vantage point. 7. The computer-implemented method of claim 6, wherein the image includes a 360 degree view horizontally around the vantage point and a 180 degree view vertically around the vantage point. 8. The computer-implemented method of claim 6, wherein obtaining image data comprises: determining the depth value of a first pixel based on a distance from the vantage point to a point on an object in the scene, wherein the first pixel is one of the pixels in the image. 9. The computer-implemented method of claim 6, wherein obtaining image data comprises: determining the depth value of a first pixel based on a field-of-view of the image or the size of objects in the scene relative to an object of known size, wherein the first pixel is one of the pixels in the image. 10. A non-transitory computer-readable storage medium for generating stereoscopic images, the non-transitory computer-readable storage medium comprising computer-executable instructions for: obtaining image data comprising directions and depth values associated with pixels in an image;generating a first vertex based on the directions and depth values associated with the pixels of the image, wherein a direction and a depth value are associated with the first vertex,generating a second vertex based on the directions and depth values associated with the pixels of the image, wherein a direction and a depth value are associated with the second vertex,wherein the directions and depth values associated with the first vertex and the second vertex are relative to an origin, andwherein the origin is common to both the first vertex and the second vertex;generating a mesh, wherein generating the mesh comprises: displacing the first vertex from the origin in a direction associated with the first vertex by a distance representative of the depth value associated with the first vertex; anddisplacing the second vertex from the origin in a direction associated with the second vertex by a distance representative of the depth value associated with the second vertex;generating a first image of the mesh from a first perspective; andgenerating a second image of the mesh from a second perspective. 11. The non-transitory computer-readable storage medium of claim 10, wherein generating a first vertex comprises: interpolating the direction and depth value of the first vertex based on the directions and depth values of the pixels surrounding the first vertex. 12. The non-transitory computer-readable storage medium of claim 10, wherein generating a mesh comprises: displacing the first vertex in a direction defined by coordinates in the horizontal direction and vertical direction. 13. The non-transitory computer-readable storage medium of claim 10, wherein the first and second perspectives are of locations near the origin. 14. The non-transitory computer-readable storage medium of claim 13, wherein the first and second perspectives are of each of two points adjacent to and approximately equal distance from the origin. 15. The non-transitory computer-readable storage medium of claim 10, wherein the image is of a scene from the perspective of a vantage point. 16. The non-transitory computer-readable storage medium of claim 15, wherein the image includes a 360 degree view horizontally around the vantage point and a 180 degree view vertically around the vantage point. 17. The non-transitory computer-readable storage medium of claim 15, wherein obtaining image data comprises: determining the depth value of a first pixel based on a distance from the vantage point to a point on an object in the scene, wherein the first pixel is one of the pixels in the image. 18. The non-transitory computer-readable storage medium of claim 15, wherein obtaining image data comprises: determining the depth value of a first pixel based on a field-of-view of the image or the size of objects in the scene relative to an object of known size, wherein the first pixel is one of the pixels in the image. 19. A system for generating stereoscopic images, the system comprising: a display; andone or more processors coupled to the display and configured to: obtain image data comprising directions and depth values associated with pixels in an image;generate a first vertex based on the directions and depth values associated with the pixels of the image, wherein a direction and a depth value are associated with the first vertex,generate a second vertex based on the directions and depth values associated with the pixels of the image, wherein a direction and a depth value are associated with the second vertex,wherein the directions and depth values associated with the first vertex and the second vertex are relative to an origin, andwherein the origin is common to both the first vertex and the second vertex;generate a mesh, wherein generating the mesh comprises: displacing the first vertex from the origin in a direction associated with the first vertex by a distance representative of the depth value associated with the first vertex; anddisplacing the second vertex from the origin in a direction associated with the second vertex by a distance representative of the depth value associated with the second vertex;generate a first image of the mesh from a first perspective; andgenerate a second image of the mesh from a second perspective. 20. The system of claim 19, wherein the display is a head-mounted display.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (4)
Herman, Brad Kenneth, Generation of three-dimensional imagery from a two-dimensional image using a depth map.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.