Rendering virtual environments utilizing full path space learning

A system comprising:

• at least one processor;
• and
• at least one non-transitory computer readable storage medium storing instructions thereon, that, when executed by the at least one processor, cause the system to:
• sample, in a virtual environment, a first plurality of paths originating from a light source to determine a first plurality of point estimations of light transfer between the light source and a camera perspective;
• determine a first global light transport function across full light paths between the light source and the camera perspective using the first plurality of point estimations by generating a first plurality of Gaussian functions estimating the first global light transport function;
• sample a second plurality of paths originating from the camera perspective to determine a second plurality of point estimations of light transfer between the light source and the camera perspective;
• determine a second global light transport function across full light paths between the light source and the camera perspective using the second plurality of point estimations by generating a second plurality of Gaussian functions estimating the second global light transport function;
• sample a third plurality of paths based on the first global light transport function and the second global light transport function by sampling a first set of paths based on the first global light transport function and a second set of paths based on the second global light transport function;
• and
• generate a digital image of the virtual environment from the camera perspective based on the first plurality of paths, the second plurality of paths, and the third plurality of paths.

A non-transitory computer readable medium storing instructions thereon that, when executed by at least one processor, cause a computer system to:

• sample, in a virtual environment, a first plurality of paths originating from a light source to determine a first plurality of point estimations of light transfer between the light source and a camera perspective;
• determine a first global light transport function across full light paths between the light source and the camera perspective using the first plurality of point estimations by generating a first plurality of Gaussian functions estimating the first global light transport function;
• sample a second plurality of paths originating from the camera perspective to determine a second plurality of point estimations of light transfer between the light source and the camera perspective;
• determine a second global light transport function across full light paths between the light source and the camera perspective using the second plurality of point estimations by generating a second plurality of Gaussian functions estimating the second global light transport function;
• sample a third plurality of paths based on the first global light transport function and the second global light transport function by sampling a first set of paths based on the first global light transport function and a second set of paths based on the second global light transport function;
• and
• generate a digital image of the virtual environment from the camera perspective based on the first plurality of paths, the second plurality of paths, and the third plurality of paths.