Method and apparatus for decoding three-dimensional scenes
Generating an image from a source image can involve encoding a projection of a part of a three-dimensional scene. Pixels of a source image comprise a depth and a color attribute. Pixels of a source image are de-projected as colored point cloud. A de-projected point in a 3D space has the color attribute of the pixel that it has been de-projected from. Also, a score is attributed to the generated point according to a local depth gradient and/or a local color gradient of the pixel it comes from, the lower the gradient, the higher the score. The generated point cloud is captured by a virtual camera for rendering on a display device. The point cloud is projected onto the viewport image by blending color of points projected on a same pixel, the blending being weighted by the scores of these points.
1. A method comprising:
de-projecting pixels of a source image as a colored point cloud, the pixels of said source image comprising a depth attribute and a color attribute, the pixels being de-projected as points having the color attribute of the respective pixel and having a score attributed according to at least one of a local depth gradient and a local color gradient of said respective pixel, wherein a lower gradient resulrs in a higher score; and
projecting said colored point cloud to generate an image and blending the color attributes of the points projected on a same pixel, said blending being weighted by the score of said points.
2. The method according to claim 1 , further comprising decoding said source image from a data stream.
3. The method according to claim 2 , further comprising:
decoding from said data stream, data representative of a mode of projection used to generate the source image, wherein the
de-projecting pixels of the source image as a colored point cloud is based in the data representative of a mode of projection.
4. The method according to claim 1 , wherein said generated image is a viewport image rendered according to a location and an orientation of a virtual camera in a 3D space.
5. The method according to claim 4 , wherein said location and orientation of the virtual camera is controlled by sensors of a head-mounted display device.
6. A device comprising a processor configured for:
de-projecting pixels of a source image as a colored point cloud, the pixels of said source image comprising a depth attribute and a color attribute, the pixels being de-projected as points having the color attribute of the respective pixel and having a score attributed according to at least one of a local depth gradient and a local color gradient of said respective pixel, wherein a lower gradient results in a higher score; and
projecting said colored point cloud to generate an image and blending the color attributes of the points projected on a same pixel, said blending being weighted by the score of said points.
7. The device according to claim 6 , wherein the processor is configured for decoding said source image from a data stream.
8. The device according to claim 7 , wherein the processor is configured for:
decoding from said data stream, data representative of a mode of projection used to generate the source image, wherein the
de-projecting pixels of the source image as a colored point cloud is based in the data representative of a mode of projection.
9. The device according to claim 6 , wherein said generated image is a viewport image rendered according to a location and an orientation of a virtual camera in a 3D space.
10. The device according to claim 9 , wherein said location and orientation of the virtual camera is controlled by sensors of a head-mounted display device.
11. A non-transitory processor readable medium having stored therein instructions for causing a processor to perform a method comprising:
de-projecting pixels of a score image as a colored point cloud, the pixels of said source image comprising a depth attribute and a color attribute, the pixels being de-projected as points having the color attribute of the respective pixel and having a score attributed according to at least one of a local depth gradient and a local color gradient of said respective pixel, wherein a lower gradient results in a higher score; and
projecting said color point cloud to generate an image and blending the color attributes of the points projected on a same pixel, sai blending being weighted by the score of said points.
12. The method according to claim 1 , wherein the color of a pixel of the generated image is the color of the point projected on the pixel having the highest score.
13. The method according to claim 1 , wherein the score of a point is a weighted sum of an inverse of the depth gradient and an inverse of the local color gradient of the de-projected pixel.
14. The device according to claim 6 , wherein the processor is configured to determine the color of a pixel of the generated image as the color of the point projected on the pixel having the highest score.
15. The device according to claim 6 , wherein the score of a point is a weighted sum of an inverse of the depth gradient and an inverse of the local color gradient of the de-projected pixel.