Generating and modifying an artificial reality environment using occlusion surfaces at predetermined distances

One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

• generate a depth map of a real environment as seen from a viewpoint of a user, the depth map comprising pixels having corresponding depth values of one or more physical objects in the real environment;
• generate, based on the depth map, a first two-dimensional occlusion mask representing at least a visible portion of the one or more physical objects that are located within a first predetermined depth range defined relative to the viewpoint;
• generate, based on the depth map, a second two-dimensional occlusion mask representing at least a visible portion of the one or more physical objects that are located within a second predetermined depth range defined relative to the viewpoint, wherein a minimum depth of the second predetermined depth range is greater than a maximum depth of the first predetermined depth range;
• pose the first and second two-dimensional occlusion masks in a three-dimensional coordinate system;
• determine a visibility of a virtual object relative to the one or more physical objects by comparing a model of the virtual object with the first and second two-dimensional occlusion masks;
• and
• generate an output image based on the determined visibility of the virtual object.

A system comprising:

• one or more processors;
• and
• one or more computer-readable storage media coupled to one or more of the processors and comprising instructions operable when executed by one or more of the processors to cause the system to:
• generate a depth map of a real environment as seen from a viewpoint of a user, the depth map comprising pixels having corresponding depth values of one or more physical objects in the real environment;
• generate, based on the depth map, a first two-dimensional occlusion mask representing at least a visible portion of the one or more physical objects that are located within a first predetermined depth range defined relative to the viewpoint;
• generate, based on the depth map, a second two-dimensional occlusion mask representing at least a visible portion of the one or more physical objects that are located within a second predetermined depth range defined relative to the viewpoint, wherein a minimum depth of the second predetermined depth range is greater than a maximum depth of the first predetermined depth range;
• pose the first and second two-dimensional occlusion masks in a three-dimensional coordinate system;
• determine a visibility of a virtual object relative to the one or more physical objects by comparing a model of the virtual object with the first and second two-dimensional occlusion masks;
• and
• generate an output image based on the determined visibility of the virtual object.