Path guiding for path-traced rendering
A computer-implemented method for generating a mask for a light source in a virtual scene includes determining a bounding box for the scene based on a frustum of a virtual camera and generating a path-traced image of the scene within the bounding box. Light paths emitted by the camera and exiting at the light source are stored, and objects poorly sampled by the light source are removed from the scene. An initial mask for the light source is generated from the density of light paths exiting at that position on the light source. The initial mask is refined by averaging in the light path density at each point on the light source for subsequent images.
1. A computer-implemented method for generating a light guide path for use in rendering virtual scenes, the computer-implemented method comprising:
under control of one or more computer systems configured with executable instructions, perform steps of:
a) placing within a scene a virtual camera having a virtual camera position, the virtual scene comprising a bounding box determined from a frustum of the virtual camera;
b) generating a mask for a light source of the scene such that each position on the light source is assigned an emission probability based on a cumulative density of light paths emitted from that position on the light source and exiting at the virtual camera position, thereby generating a masked light source data structure wherein light paths are emitted from the light source anisotropically, wherein the cumulative density is set to zero for positions on the light source that are incapable of emitting into the bounding box;
c) generating a path-traced image by using the masked light source data structure to generate an anisotropic plurality of light paths and storing an exiting path subset comprising the light paths of the anisotropic plurality of light paths that exit at the virtual camera;
d) using quad trees to identify a light paths subset of the exiting path subset that are sampled less than a pre-determined threshold;
e) for at least some light path of the light paths subset:
1) computing a distribution for at least one vertex of a first plurality of vertices of the light path;
2) using the distributions, sampling a position for at least one other vertex of the first plurality of vertices;
3) constructing a guided light path from the sampled positions of the at least one vertex of the first plurality of vertices; and
4) modifying the guided light path by iteratively sampling the positions of a second plurality of vertices along the guided light path until the guided light path is visible to the virtual camera;
f) constructing a path-guided image using only the modified guided light paths; and
g) combining the path-traced image with the path-guided image to form a scene image storage in computer memory.
2. The computer-implemented method of claim 1 , wherein the distribution of each vertex of the second plurality of vertices comprises a 2D Gaussian distribution.
3. The computer-implemented method of claim 1 , wherein the distribution of each vertex of the second plurality of vertices comprises an anisotropic reconstruction kernel.
4. The computer-implemented method of claim 1 , further comprising: if a termination/splitting factor is greater than 1, splitting the guided light path into at least two guide paths.
5. The computer-implemented method of claim 4 , wherein splitting the guided light path comprises resampling two vertices of the second plurality of vertices for each distribution.
6. The computer-implemented method of claim 1 , further comprising: if a termination/splitting factor is less than 1, terminating the guided light path.
7. The computer-implemented method of claim 6 , wherein terminating the guided light path comprises deleting at least some vertices of the guided light path.
8. The computer-implemented method of claim 1 , wherein the guided light paths comprise diffuse reflection, diffuse refraction, or caustics.
9. The computer-implemented method of claim 8 , further comprising denoising at least one of the path-traced image or the path guided image.
10. The computer-implemented method of claim 9 , wherein the denoising comprises density-based outlier rejection.
11. A computer system for modeling surfaces of virtual objects, the system comprising:
at least one processor; and
a computer-readable medium storing instructions, which when executed by the at least one processor, causes the system to carry out the method of claim 1 .
12. A non-transitory computer-readable storage medium storing instructions, which when executed by at least one processor of a computer system, causes the computer system to carry out the method of claim 1 .