Determining a visual hull of an object

A computing system, comprising:

• a computing device processor;
• a camera associated with a set of camera parameters;
• a memory device including instructions that, when executed by the computing device processor, enable the computing system to:
• capture image data using the camera, the image data including a representation of an object from a plurality of viewpoints, the object having a surface defining a volume of the object, the object being associated with a reference coordinate system;
• generate a segmentation mask from the image data, the segmentation mask including a contour of the object;
• identify a region that includes the object, the region partitioned into a plurality of sub regions, individual sub regions associated with a respective position in the reference coordinate system;
• identify a point in the segmentation mask associated with a sub region based at least in part on the set of camera parameters, the point included within a window;
• and
• determine a probability value of the sub region being inside the volume of the object based at least in part on one of a level of uncertainty in one of the camera parameters or the segmentation mask.

A method, comprising:

• capturing image data using a camera, the image data including a representation of an object from a plurality of viewpoints, the object having a surface defining a volume of the object, the object being associated with a reference coordinate system;
• generating a segmentation mask from the image data, the segmentation mask including a contour of the object;
• identifying a region that includes the object, the region partitioned into a plurality of sub regions, individual sub regions associated with a respective position in a reference coordinate system associated with the object;
• identifying a point in the segmentation mask associated with a sub region based at least in part on a set of camera parameters associated with the camera, the point included within a window;
• and
• determining a probability value of the sub region being inside the volume of the object based at least in part on a level of uncertainty in one of the camera parameters or the segmentation mask.