Concave surface modeling in image-based visual hull
View Patent ↗Apparatus and methods disclosed herein provide for a set of reference images obtained from a camera and a reference image obtained from a viewpoint to capture an entire concave region of an object; a silhouette processing module for obtaining a silhouette image of the concave region of the object; and a virtual-image synthesis module connected to the silhouette processing module for synthesizing a virtual inside-out image of the concave region from the computed silhouette images and for generating a visual hull of the object having the concave region.
1. An apparatus, comprising:
a storage medium configured to store a plurality of reference images of an object comprising a concave region;
a silhouette processing module configured to:
obtain the plurality of reference images from the storage medium, and
obtain a silhouette fur each of the plurality of reference images; and
a virtual-image synthesis module configured to:
generate a visual bull for the object having the concave region based on the silhouette for each of the plurality of reference images,
select a virtual camera position within the concave region, and
generate a virtual inside-out image of the concave region based on the visual hull and the virtual camera position.
2. The apparatus of claim 1 , wherein the silhouette processing module is further configured to generate an image comprising a boundary of the concave region of the object.
3. The apparatus of claim 2 , wherein the silhouette processing module is further configured to obtain a boundary silhouette for the boundary of the concave region.
4. The apparatus of claim 2 , wherein the virtual-image synthesis module is further configured to determine three-dimensional coordinates of the boundary of the concave region on the visual hull.
5. The apparatus of claim 2 , wherein the silhouette processing module performs image segmentation on one of the plurality of reference images of the object to generate the image comprising the boundary of the concave region of the object.
6. The apparatus of claim 1 , wherein each of the plurality of reference images of the object is taken from a perspective of an outside of the object.
7. A method comprising:
obtaining a plurality of reference images of an object comprising a concave region;
obtaining a silhouette for each of the plurality of reference images;
generating a visual hull for the object having the concave region based on the silhouette for each of the plurality of reference images;
selecting a virtual camera position within the concave region; and
generating a virtual inside-out image of the concave region based on the visual hull and the virtual camera position.
8. The method of claim 7 , further comprising generating an image comprising a boundary of the concave region of the object.
9. The method of claim 8 , further comprising obtaining a boundary silhouette for the boundary of the concave region.
10. The method of claim 8 , further comprising determining three-dimensional coordinates of the boundary of the concave region on the visual hull.
11. The method of claim 8 , further comprising performing image segmentation on one of the plurality of reference images of the object to generate the image comprising the boundary of the concave region of the object.
12. The method of claim 7 , wherein each of the plurality of reference images of the object is taken from a perspective of an outside of the object.
13. A non-transitory computer-readable storage medium storing a computer executable program code that, when executed by a processor, causes the processor to:
obtain a plurality of reference images of an object comprising a concave region;
obtain a silhouette for each of the plurality of reference images; and
generate a visual hull for the object having the concave region based on the silhouette for each of the plurality of reference images;
select a virtual camera position within the concave region; and
generate a virtual inside-out image of the concave region based on the visual hull and the virtual camera position.
14. The non-transitory computer-readable storage medium of claim 13 , wherein the executable program code further causes the processor to generate an image comprising a boundary of the concave region of the object.
15. The non-transitory computer-readable storage medium of claim 14 , wherein the executable program code further causes the processor to obtain a boundary silhouette for the boundary of the concave region.
16. The non-transitory computer-readable storage medium of claim 14 , wherein the executable program code further causes the processor to determine three-dimensional coordinates of the boundary of the concave region on the visual hull.
17. The non-transitory computer-readable storage medium of claim 14 , wherein the executable program code further causes the processor to perform image segmentation on one of the plurality of reference images of the object to generate the image comprising the boundary of the concave region of the object.