1. A method comprising:
obtaining a plurality of live images, the live images comprising a tracked object;
determining, for a live image in the plurality of live images, a camera pose relative to the tracked object;
rendering, based on the camera pose, a plurality of synthetic images without the tracked object, each synthetic image obtained from a distinct keyframe in a 3D model;
comparing the live and synthetic images to determine a first mask region associated with the tracked object;
computing optical flow magnitudes for a plurality of pixels in a first mask region associated with the tracked object relative to a subset of synthetic images in the plurality of synthetic images;
determining, for each of the plurality of pixels in the first mask, a corresponding pixel in each of the subset of synthetic images based, in part, on the optical flow magnitude; and
determining replacement pixels for each of the plurality of pixels in the first mask, each replacement pixel corresponding to a distinct pixel in the first mask, wherein each replacement pixel is determined as a function of the corresponding pixels in the subset of synthetic images that correspond to pixel in the first mask.
2. The method of claim 1, further comprising rendering a diminished reality image, the diminished reality image obtained based, at least in part, on the replacement pixels.
3. The method of claim 2, further comprising, rendering a virtual object in a region in the image indicated by the first mask, the virtual object being rendered based on the current camera pose.
4. The method of claim 3, wherein rendering the virtual object in the region in the image indicated by first mask comprises:
rendering a virtual representation of at least one known real object in the image, into a virtual z-buffer, the real object at least partially in the first mask;
resolving occlusions between the at least one known real object and the virtual object in the virtual z-buffer; and
warping the virtual z-buffer to match the image, the warping based, in part, on an optical flow between the virtual representation of the at least one known real object and the at least one real object in the image.
5. The method of claim 1, wherein determining a corresponding pixel in each of the subset of synthetic images comprises:
obtaining, for each of the plurality of pixels in the first mask, a displacement and intensity correction based on the optical flow.
6. The method of claim 1, wherein:
each replacement pixel is determined as a weighted average of corresponding pixels in the subset of synthetic images, wherein the weight associated with a corresponding pixel in a synthetic image in the subset, is based, in part, on the optical flow magnitude for the corresponding pixel, and the angular displacement between the live image and the synthetic image associated with the corresponding pixel.
7. The method of claim 6, wherein the first mask (M\u2032) region comprises a second mask region (M) around the tracked object and wherein the optical flow magnitude for each replacement pixel in M is determined by scattered data interpolation from the boundary M\u2032-M.
8. The method of claim 1, wherein the plurality of synthetic images and the subset of the plurality of synthetic images each comprise three synthetic images.
9. The method of claim 1, wherein Simultaneous Localization and Mapping (SLAM) tracking techniques are used to determine the camera pose.
10. A Mobile Station (MS) comprising:
a camera configured to capture a plurality of live images comprising a tracked object,
a memory, the memory to store a 3D model comprising a plurality of keyframes, and
a processor coupled to the camera and the memory, the processor configured to:
determine, for a live image in the plurality of images, a camera pose relative to the tracked object;
render, based on the camera pose, a plurality of synthetic images without the tracked object, each synthetic image obtained from a distinct keyframe;
compare the live and synthetic images to determine a first mask region associated with the tracked object;
compute optical flow magnitudes for a plurality of pixels in a first mask region associated with the tracked object relative to a subset of synthetic images in the plurality of synthetic images;
determine, for each of the plurality of pixels in the first mask, a corresponding pixel in each of the subset of synthetic images based, in part, on the optical flow magnitude; and
determine replacement pixels for each of the plurality of pixels in the first mask, each replacement pixel corresponding to a distinct pixel in the first mask, wherein each replacement pixel is determined as a function of the corresponding pixels in the subset of synthetic images that correspond to the pixel in the first mask.
11. The MS of claim 10, wherein the processor is further configured to:
render a diminished reality image, the diminished reality image obtained based, at least in part, on the replacement pixels.
12. The MS of claim 11, wherein the processor is further configured to:
render a virtual object in a region in the image indicated by the first mask, the virtual object being rendered based on the current camera pose.
13. The MS of claim 12, wherein to render the virtual object in the region in the image indicated by first mask, the processor is configured to:
render a virtual representation of at least one known real object in the image, into a virtual z-buffer, the real object at least partially in the first mask;
resolve occlusions between the at least one known real object and the virtual object in the virtual z-buffer; and
warp the virtual z-buffer to match the image, the warping based, in part, on an optical flow between the virtual representation of the at least one known real object and the at least one real object in the image.
14. The MS of claim 10, wherein to determine a corresponding pixel in each of the subset of synthetic images, the processor is configured to:
obtain, for each of the plurality of pixels in the first mask, a displacement and intensity correction based on the optical flow.
15. The MS of claim 10, wherein:
each replacement pixel is determined as a weighted average of corresponding pixels in the subset of synthetic images, wherein the weight associated with a corresponding pixel in a synthetic image in the subset, is based, in part, on the optical flow magnitude for the corresponding pixel, and the angular displacement between the live image and the synthetic image associated with the corresponding pixel.
16. The MS of claim 15, wherein:
the first mask (M\u2032) region comprises a second mask region (M) around the tracked object and wherein the optical flow magnitude for each replacement pixel in M is determined by scattered data interpolation from the boundary M\u2032-M.
17. The MS of claim 10, wherein the plurality of synthetic images and the subset of the plurality of synthetic images each comprise three synthetic images.
18. The MS of claim 10, wherein the processor is configured to determine the camera pose using Simultaneous Localization and Mapping (SLAM) tracking techniques.
19. An apparatus comprising:
imaging means, the imaging means to capture a plurality of images comprising a tracked object,
storage means, the storage means to store a 3D model comprising a plurality of keyframes, and
processing means, the processing means coupled to the imaging means and the storage means, the processing means further comprising:
means for determining, for a live image in the plurality of live images, an imaging means pose relative to the tracked object;
means for rendering, based on the imaging means pose, a plurality of synthetic images without the tracked object, each synthetic image obtained from a distinct keyframe;
means for comparing the live and synthetic images to determine a first mask region associated with the tracked object;
means for computing optical flow magnitudes for a plurality of pixels in a first mask region associated with the tracked object relative to a subset of synthetic images in the plurality of synthetic images;
means for determining, for each of the plurality of pixels in the first mask, a corresponding pixel in each of the subset of synthetic images based, in part, on the optical flow magnitude; and
means for determining replacement pixels for each of the plurality of pixels in the first mask, each replacement pixel corresponding to a distinct pixel in the first mask, wherein each replacement pixel is determined as a function of the corresponding pixels in the subset of synthetic images that correspond to the pixel in the first mask.
20. The apparatus of claim 19, wherein the processing means further comprises:
means for rendering a diminished reality image, the diminished reality image obtained based, at least in part, on the replacement pixels.
21. The apparatus of claim 20, wherein the processing means further comprises:
means for rendering a virtual object in a region in the image indicated by the first mask, the virtual object being rendered based on the current camera pose.
22. The apparatus of claim 21, wherein means for rendering the virtual object in the region in the image indicated by first mask comprises:
means for rendering a virtual representation of at least one known real object in the image, into a virtual z-buffer, the real object at least partially in the first mask;
means for resolving occlusions between the at least one known real object and the virtual object in the virtual z-buffer; and
means for warping the virtual z-buffer to match the image, the warping based, in part, on an optical flow between the virtual representation of the at least one known real object and the at least one real object in the image.
23. The apparatus of claim 19, wherein:
each replacement pixel is determined as a weighted average of corresponding pixels in the subset of synthetic images, wherein the weight associated with a corresponding pixel in a synthetic image in the subset, is based, in part, on the optical flow magnitude for the corresponding pixel, and the angular displacement between the live image and the synthetic image associated with the corresponding pixel.
24. A non-transitory computer-readable medium comprising instructions, which, when executed by a processor, perform steps in a method comprising:
obtaining a plurality of live images, the live images comprising a tracked object;
determining, for a live image in the plurality of live images, a camera pose relative to the tracked object;
rendering, based on the camera pose, a plurality of synthetic images without the tracked object, each synthetic image obtained from a distinct keyframe in a 3D model based on the camera pose;
comparing the live and synthetic images to determine a first mask region associated with the tracked object;
computing optical flow magnitudes for a plurality of pixels in a first mask region associated with the tracked object relative to a subset of synthetic images in the plurality of synthetic images;
determining, for each of the plurality of pixels in the first mask, a corresponding pixel in each of the subset of synthetic images based, in part, on the optical flow magnitude; and
determining replacement pixels for each of the plurality of pixels in the first mask, each replacement pixel corresponding to a distinct pixel in the first mask, wherein each replacement pixel is determined as a function of the corresponding pixels in the subset of synthetic images that correspond to the pixel in the first mask.
25. The computer-readable medium of claim 24, further comprising rendering a diminished reality image, the diminished reality image obtained based, at least in part, on the replacement pixels.
26. The computer-readable medium of claim 25, further comprising, rendering a virtual object in a region in the image indicated by the first mask, the virtual object being rendered based on the current camera pose.
27. The computer-readable medium of claim 26, wherein rendering the virtual object in the region in the image indicated by first mask comprises:
rendering a virtual representation of at least one known real object in the image, into a virtual z-buffer, the real object at least partially in the first mask;
resolving occlusions between the at least one known real object and the virtual object in the virtual z-buffer; and
warping the virtual z-buffer to match the image, the warping based, in part, on an optical flow between the virtual representation of the at least one known real object and the at least one real object in the image.
28. The computer-readable medium of claim 24, wherein determining a corresponding pixel in each of the subset of synthetic images comprises:
obtaining, for each of the plurality of pixels in the first mask, a displacement and intensity correction based on the optical flow.
29. The computer-readable medium of claim 24, wherein:
each replacement pixel is determined as a weighted average of corresponding pixels in the subset of synthetic images, wherein the weight associated with a corresponding pixel in a synthetic image in the subset, is based, in part, on the optical flow magnitude for the corresponding pixel, and the angular displacement between the live image and the synthetic image associated with the corresponding pixel.
30. The computer-readable medium of claim 29, wherein the first mask (M\u2032) region comprises a second mask region (M) around the tracked object and wherein the optical flow magnitude for each replacement pixel in M is determined by scattered data interpolation from the boundary M\u2032-M.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
What is claimed is:
1. A nonwoven fabric exhibiting cross-direction extensibility and recovery, comprising:
a nonwoven web comprising staple length fibers of about 0.8 to 3.0 denier having a basis weight of about 1.0 to 4.0 ounces per square yard; and
a polymeric binder composition substantially uniformly applied to said nonwoven web,
said fabric having a machine direction and a cross-direction, and exhibiting at least about 50% extensibility in said cross-direction and at least about 90% recovery in the cross direction.
2. A nonwoven fabric in accordance with claim 1, wherein
said nonwoven web comprises fibers of about 1.5 denier, said web having a basis weight of about 2.5 to 3.5 ounces per square yard.
3. A nonwoven fabric in accordance with claim 1, wherein
said fabric exhibits a ratio of machine direction tensile strength to cross-direction tensile strength of about 1:1 to about 3:1.
4. A nonwoven fabric in accordance with claim 1, wherein
said binder composition comprises between about 17% and about 31%, by weight, of acrylic binder.
5. A nonwoven fabric in accordance with claim 1, wherein
said fabric exhibits a rectilinear pattern oriented at an angle between about 30 and 60 relative to said machine direction.
6. A mattress pad assembly, comprising:
a generally rectangular upper pad; and
a peripheral nonwoven fabric extending about and secured to said upper pad at the periphery thereof, said fabric having a machine direction and a cross-direction, said fabric extending about said upper pad in said machine direction;
said nonwoven fabric comprising a nonwoven web of staple length fibers of about 0.8 to 3.0 denier having a basis weight of about 1.0 to 4.0 ounces per square yard; and
a polymeric binder composition substantially uniformly applied to said nonwoven web, said binder composition comprising between about 17% and about 31% , by weight, of acrylic binder,
said fabric exhibiting at least about 50% extensibility in said cross-direction and at least about 90% recovery in the cross-direction.
7. A mattress pad assembly in accordance with claim 6, including:
at least one elongate elastic element secured to said nonwoven fabric at a marginal portion thereof opposite said upper pad.
8. A mattress pad assembly in accordance with claim 6, wherein
said nonwoven fabric comprises a single piece of material extending about the periphery of said upper pad.
9. A mattress pat assembly in accordance with claim 6, wherein:
said nonwoven fabric exhibits a rectilinear pattern oriented at an angle between about 30 and 60 relative to said machine direction;
said fabric exhibiting a ratio of cross-direction tensile strength to machine direction tensile strength of about 2:1.
10. A method of making a nonwoven fabric exhibiting cross-direction extensibility and recovery, comprising the steps of:
providing a nonwoven web comprising staple length fibers of about 0.8 to 3.0 denier having a basis weight of about 1.0 to 4.0 ounces per square yard;
hydroentangling said nonwoven web;
applying a polymeric binder composition substantially uniformly to said nonwoven web;
drying said nonwoven web to form said nonwoven fabric with said binder composition comprising between about 17% and 31%, by weight, of said acrylic binder, said fabric having a machine direction and a cross-direction, and exhibiting at least about 50% extensibility in said cross-direction, and at least about 90% recovery in the cross-direction; and a ratio of machine direction tensile strength to cross-direction tensile strength of about 1:1 to 3:1.
11. A method of making a nonwoven fabric, wherein:
said hydroentangling step includes forming a rectilinear pattern in said nonwoven web oriented at between about 30 to 60 relative to said machine direction.
12. A method of making a nonwoven fabric in accordance with claim 11, wherein:
said hydroentangling step includes hydroentangling said nonwoven web prior to forming said rectilinear pattern.