Files
test/intern/cycles/kernel/integrator/subsurface.h

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

206 lines
7.1 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: Apache-2.0
* Copyright 2011-2022 Blender Foundation */
#pragma once
#include "kernel/camera/projection.h"
#include "kernel/bvh/bvh.h"
#include "kernel/closure/alloc.h"
#include "kernel/closure/bsdf_diffuse.h"
#include "kernel/closure/bsdf_principled_diffuse.h"
#include "kernel/closure/bssrdf.h"
#include "kernel/closure/volume.h"
#include "kernel/integrator/intersect_volume_stack.h"
#include "kernel/integrator/path_state.h"
#include "kernel/integrator/subsurface_disk.h"
#include "kernel/integrator/subsurface_random_walk.h"
#include "kernel/integrator/surface_shader.h"
CCL_NAMESPACE_BEGIN
#ifdef __SUBSURFACE__
ccl_device int subsurface_bounce(KernelGlobals kg,
IntegratorState state,
Cycles: Kernel address space changes for MSL This is the first of a sequence of changes to support compiling Cycles kernels as MSL (Metal Shading Language) in preparation for a Metal GPU device implementation. MSL requires that all pointer types be declared with explicit address space attributes (device, thread, etc...). There is already precedent for this with Cycles' address space macros (ccl_global, ccl_private, etc...), therefore the first step of MSL-enablement is to apply these consistently. Line-for-line this represents the largest change required to enable MSL. Applying this change first will simplify future patches as well as offering the emergent benefit of enhanced descriptiveness. The vast majority of deltas in this patch fall into one of two cases: - Ensuring ccl_private is specified for thread-local pointer types - Ensuring ccl_global is specified for device-wide pointer types Additionally, the ccl_addr_space qualifier can be removed. Prior to Cycles X, ccl_addr_space was used as a context-dependent address space qualifier, but now it is either redundant (e.g. in struct typedefs), or can be replaced by ccl_global in the case of pointer types. Associated function variants (e.g. lcg_step_float_addrspace) are also redundant. In cases where address space qualifiers are chained with "const", this patch places the address space qualifier first. The rationale for this is that the choice of address space is likely to have the greater impact on runtime performance and overall architecture. The final part of this patch is the addition of a metal/compat.h header. This is partially complete and will be extended in future patches, paving the way for the full Metal implementation. Ref T92212 Reviewed By: brecht Maniphest Tasks: T92212 Differential Revision: https://developer.blender.org/D12864
2021-10-14 13:53:40 +01:00
ccl_private ShaderData *sd,
ccl_private const ShaderClosure *sc)
{
/* We should never have two consecutive BSSRDF bounces, the second one should
* be converted to a diffuse BSDF to avoid this. */
kernel_assert(!(INTEGRATOR_STATE(state, path, flag) & PATH_RAY_DIFFUSE_ANCESTOR));
/* Setup path state for intersect_subsurface kernel. */
Cycles: Kernel address space changes for MSL This is the first of a sequence of changes to support compiling Cycles kernels as MSL (Metal Shading Language) in preparation for a Metal GPU device implementation. MSL requires that all pointer types be declared with explicit address space attributes (device, thread, etc...). There is already precedent for this with Cycles' address space macros (ccl_global, ccl_private, etc...), therefore the first step of MSL-enablement is to apply these consistently. Line-for-line this represents the largest change required to enable MSL. Applying this change first will simplify future patches as well as offering the emergent benefit of enhanced descriptiveness. The vast majority of deltas in this patch fall into one of two cases: - Ensuring ccl_private is specified for thread-local pointer types - Ensuring ccl_global is specified for device-wide pointer types Additionally, the ccl_addr_space qualifier can be removed. Prior to Cycles X, ccl_addr_space was used as a context-dependent address space qualifier, but now it is either redundant (e.g. in struct typedefs), or can be replaced by ccl_global in the case of pointer types. Associated function variants (e.g. lcg_step_float_addrspace) are also redundant. In cases where address space qualifiers are chained with "const", this patch places the address space qualifier first. The rationale for this is that the choice of address space is likely to have the greater impact on runtime performance and overall architecture. The final part of this patch is the addition of a metal/compat.h header. This is partially complete and will be extended in future patches, paving the way for the full Metal implementation. Ref T92212 Reviewed By: brecht Maniphest Tasks: T92212 Differential Revision: https://developer.blender.org/D12864
2021-10-14 13:53:40 +01:00
ccl_private const Bssrdf *bssrdf = (ccl_private const Bssrdf *)sc;
/* Setup ray into surface. */
INTEGRATOR_STATE_WRITE(state, ray, P) = sd->P;
INTEGRATOR_STATE_WRITE(state, ray, D) = bssrdf->N;
INTEGRATOR_STATE_WRITE(state, ray, tmin) = 0.0f;
INTEGRATOR_STATE_WRITE(state, ray, tmax) = FLT_MAX;
INTEGRATOR_STATE_WRITE(state, ray, dP) = differential_make_compact(sd->dP);
INTEGRATOR_STATE_WRITE(state, ray, dD) = differential_zero_compact();
/* Pass along object info, reusing isect to save memory. */
INTEGRATOR_STATE_WRITE(state, subsurface, Ng) = sd->Ng;
uint32_t path_flag = (INTEGRATOR_STATE(state, path, flag) & ~PATH_RAY_CAMERA) |
((sc->type == CLOSURE_BSSRDF_BURLEY_ID) ? PATH_RAY_SUBSURFACE_DISK :
PATH_RAY_SUBSURFACE_RANDOM_WALK);
/* Compute weight, optionally including Fresnel from entry point. */
Spectrum weight = surface_shader_bssrdf_sample_weight(sd, sc);
if (bssrdf->roughness != FLT_MAX) {
path_flag |= PATH_RAY_SUBSURFACE_USE_FRESNEL;
}
if (sd->flag & SD_BACKFACING) {
path_flag |= PATH_RAY_SUBSURFACE_BACKFACING;
}
INTEGRATOR_STATE_WRITE(state, path, throughput) *= weight;
INTEGRATOR_STATE_WRITE(state, path, flag) = path_flag;
/* Advance random number offset for bounce. */
INTEGRATOR_STATE_WRITE(state, path, rng_offset) += PRNG_BOUNCE_NUM;
if (kernel_data.kernel_features & KERNEL_FEATURE_LIGHT_PASSES) {
if (INTEGRATOR_STATE(state, path, bounce) == 0) {
INTEGRATOR_STATE_WRITE(state, path, pass_diffuse_weight) = one_spectrum();
INTEGRATOR_STATE_WRITE(state, path, pass_glossy_weight) = zero_spectrum();
}
}
/* Pass BSSRDF parameters. */
INTEGRATOR_STATE_WRITE(state, subsurface, albedo) = bssrdf->albedo;
INTEGRATOR_STATE_WRITE(state, subsurface, radius) = bssrdf->radius;
INTEGRATOR_STATE_WRITE(state, subsurface, anisotropy) = bssrdf->anisotropy;
/* Path guiding. */
guiding_record_bssrdf_weight(kg, state, weight, bssrdf->albedo);
return LABEL_SUBSURFACE_SCATTER;
}
ccl_device void subsurface_shader_data_setup(KernelGlobals kg,
IntegratorState state,
Cycles: Kernel address space changes for MSL This is the first of a sequence of changes to support compiling Cycles kernels as MSL (Metal Shading Language) in preparation for a Metal GPU device implementation. MSL requires that all pointer types be declared with explicit address space attributes (device, thread, etc...). There is already precedent for this with Cycles' address space macros (ccl_global, ccl_private, etc...), therefore the first step of MSL-enablement is to apply these consistently. Line-for-line this represents the largest change required to enable MSL. Applying this change first will simplify future patches as well as offering the emergent benefit of enhanced descriptiveness. The vast majority of deltas in this patch fall into one of two cases: - Ensuring ccl_private is specified for thread-local pointer types - Ensuring ccl_global is specified for device-wide pointer types Additionally, the ccl_addr_space qualifier can be removed. Prior to Cycles X, ccl_addr_space was used as a context-dependent address space qualifier, but now it is either redundant (e.g. in struct typedefs), or can be replaced by ccl_global in the case of pointer types. Associated function variants (e.g. lcg_step_float_addrspace) are also redundant. In cases where address space qualifiers are chained with "const", this patch places the address space qualifier first. The rationale for this is that the choice of address space is likely to have the greater impact on runtime performance and overall architecture. The final part of this patch is the addition of a metal/compat.h header. This is partially complete and will be extended in future patches, paving the way for the full Metal implementation. Ref T92212 Reviewed By: brecht Maniphest Tasks: T92212 Differential Revision: https://developer.blender.org/D12864
2021-10-14 13:53:40 +01:00
ccl_private ShaderData *sd,
const uint32_t path_flag)
{
/* Get bump mapped normal from shader evaluation at exit point. */
float3 N = sd->N;
if (sd->flag & SD_HAS_BSSRDF_BUMP) {
N = surface_shader_bssrdf_normal(sd);
}
/* Setup diffuse BSDF at the exit point. This replaces shader_eval_surface. */
sd->flag &= ~SD_CLOSURE_FLAGS;
sd->num_closure = 0;
sd->num_closure_left = kernel_data.max_closures;
const Spectrum weight = one_spectrum();
if (path_flag & PATH_RAY_SUBSURFACE_USE_FRESNEL) {
Cycles: Kernel address space changes for MSL This is the first of a sequence of changes to support compiling Cycles kernels as MSL (Metal Shading Language) in preparation for a Metal GPU device implementation. MSL requires that all pointer types be declared with explicit address space attributes (device, thread, etc...). There is already precedent for this with Cycles' address space macros (ccl_global, ccl_private, etc...), therefore the first step of MSL-enablement is to apply these consistently. Line-for-line this represents the largest change required to enable MSL. Applying this change first will simplify future patches as well as offering the emergent benefit of enhanced descriptiveness. The vast majority of deltas in this patch fall into one of two cases: - Ensuring ccl_private is specified for thread-local pointer types - Ensuring ccl_global is specified for device-wide pointer types Additionally, the ccl_addr_space qualifier can be removed. Prior to Cycles X, ccl_addr_space was used as a context-dependent address space qualifier, but now it is either redundant (e.g. in struct typedefs), or can be replaced by ccl_global in the case of pointer types. Associated function variants (e.g. lcg_step_float_addrspace) are also redundant. In cases where address space qualifiers are chained with "const", this patch places the address space qualifier first. The rationale for this is that the choice of address space is likely to have the greater impact on runtime performance and overall architecture. The final part of this patch is the addition of a metal/compat.h header. This is partially complete and will be extended in future patches, paving the way for the full Metal implementation. Ref T92212 Reviewed By: brecht Maniphest Tasks: T92212 Differential Revision: https://developer.blender.org/D12864
2021-10-14 13:53:40 +01:00
ccl_private PrincipledDiffuseBsdf *bsdf = (ccl_private PrincipledDiffuseBsdf *)bsdf_alloc(
sd, sizeof(PrincipledDiffuseBsdf), weight);
if (bsdf) {
bsdf->N = N;
bsdf->roughness = FLT_MAX;
sd->flag |= bsdf_principled_diffuse_setup(bsdf, PRINCIPLED_DIFFUSE_LAMBERT_EXIT);
}
}
else {
Cycles: Kernel address space changes for MSL This is the first of a sequence of changes to support compiling Cycles kernels as MSL (Metal Shading Language) in preparation for a Metal GPU device implementation. MSL requires that all pointer types be declared with explicit address space attributes (device, thread, etc...). There is already precedent for this with Cycles' address space macros (ccl_global, ccl_private, etc...), therefore the first step of MSL-enablement is to apply these consistently. Line-for-line this represents the largest change required to enable MSL. Applying this change first will simplify future patches as well as offering the emergent benefit of enhanced descriptiveness. The vast majority of deltas in this patch fall into one of two cases: - Ensuring ccl_private is specified for thread-local pointer types - Ensuring ccl_global is specified for device-wide pointer types Additionally, the ccl_addr_space qualifier can be removed. Prior to Cycles X, ccl_addr_space was used as a context-dependent address space qualifier, but now it is either redundant (e.g. in struct typedefs), or can be replaced by ccl_global in the case of pointer types. Associated function variants (e.g. lcg_step_float_addrspace) are also redundant. In cases where address space qualifiers are chained with "const", this patch places the address space qualifier first. The rationale for this is that the choice of address space is likely to have the greater impact on runtime performance and overall architecture. The final part of this patch is the addition of a metal/compat.h header. This is partially complete and will be extended in future patches, paving the way for the full Metal implementation. Ref T92212 Reviewed By: brecht Maniphest Tasks: T92212 Differential Revision: https://developer.blender.org/D12864
2021-10-14 13:53:40 +01:00
ccl_private DiffuseBsdf *bsdf = (ccl_private DiffuseBsdf *)bsdf_alloc(
sd, sizeof(DiffuseBsdf), weight);
if (bsdf) {
bsdf->N = N;
sd->flag |= bsdf_diffuse_setup(bsdf);
}
}
}
ccl_device_inline bool subsurface_scatter(KernelGlobals kg, IntegratorState state)
{
RNGState rng_state;
path_state_rng_load(state, &rng_state);
Ray ray ccl_optional_struct_init;
LocalIntersection ss_isect ccl_optional_struct_init;
if (INTEGRATOR_STATE(state, path, flag) & PATH_RAY_SUBSURFACE_RANDOM_WALK) {
if (!subsurface_random_walk(kg, state, rng_state, ray, ss_isect)) {
return false;
}
}
else {
if (!subsurface_disk(kg, state, rng_state, ray, ss_isect)) {
return false;
}
}
# ifdef __VOLUME__
/* Update volume stack if needed. */
if (kernel_data.integrator.use_volumes) {
const int object = ss_isect.hits[0].object;
const int object_flag = kernel_data_fetch(object_flag, object);
if (object_flag & SD_OBJECT_INTERSECTS_VOLUME) {
float3 P = INTEGRATOR_STATE(state, ray, P);
integrator_volume_stack_update_for_subsurface(kg, state, P, ray.P);
}
}
# endif /* __VOLUME__ */
/* Pretend ray is coming from the outside towards the exit point. This ensures
* correct front/back facing normals.
* TODO: find a more elegant solution? */
ray.P += ray.D * ray.tmax * 2.0f;
ray.D = -ray.D;
integrator_state_write_isect(kg, state, &ss_isect.hits[0]);
integrator_state_write_ray(kg, state, &ray);
/* Advance random number offset for bounce. */
INTEGRATOR_STATE_WRITE(state, path, rng_offset) += PRNG_BOUNCE_NUM;
const int shader = intersection_get_shader(kg, &ss_isect.hits[0]);
const int shader_flags = kernel_data_fetch(shaders, shader).flags;
Cycles: approximate shadow caustics using manifold next event estimation This adds support for selective rendering of caustics in shadows of refractive objects. Example uses are rendering of underwater caustics and eye caustics. This is based on "Manifold Next Event Estimation", a method developed for production rendering. The idea is to selectively enable shadow caustics on a few objects in the scene where they have a big visual impact, without impacting render performance for the rest of the scene. The Shadow Caustic option must be manually enabled on light, caustic receiver and caster objects. For such light paths, the Filter Glossy option will be ignored and replaced by sharp caustics. Currently this method has a various limitations: * Only caustics in shadows of refractive objects work, which means no caustics from reflection or caustics that outside shadows. Only up to 4 refractive caustic bounces are supported. * Caustic caster objects should have smooth normals. * Not currently support for Metal GPU rendering. In the future this method may be extended for more general caustics. TECHNICAL DETAILS This code adds manifold next event estimation through refractive surface(s) as a new sampling technique for direct lighting, i.e. finding the point on the refractive surface(s) along the path to a light sample, which satisfies Fermat's principle for a given microfacet normal and the path's end points. This technique involves walking on the "specular manifold" using a pseudo newton solver. Such a manifold is defined by the specular constraint matrix from the manifold exploration framework [2]. For each refractive interface, this constraint is defined by enforcing that the generalized half-vector projection onto the interface local tangent plane is null. The newton solver guides the walk by linearizing the manifold locally before reprojecting the linear solution onto the refractive surface. See paper [1] for more details about the technique itself and [3] for the half-vector light transport formulation, from which it is derived. [1] Manifold Next Event Estimation Johannes Hanika, Marc Droske, and Luca Fascione. 2015. Comput. Graph. Forum 34, 4 (July 2015), 87–97. https://jo.dreggn.org/home/2015_mnee.pdf [2] Manifold exploration: a Markov Chain Monte Carlo technique for rendering scenes with difficult specular transport Wenzel Jakob and Steve Marschner. 2012. ACM Trans. Graph. 31, 4, Article 58 (July 2012), 13 pages. https://www.cs.cornell.edu/projects/manifolds-sg12/ [3] The Natural-Constraint Representation of the Path Space for Efficient Light Transport Simulation. Anton S. Kaplanyan, Johannes Hanika, and Carsten Dachsbacher. 2014. ACM Trans. Graph. 33, 4, Article 102 (July 2014), 13 pages. https://cg.ivd.kit.edu/english/HSLT.php The code for this samping technique was inserted at the light sampling stage (direct lighting). If the walk is successful, it turns off path regularization using a specialized flag in the path state (PATH_MNEE_SUCCESS). This flag tells the integrator not to blur the brdf roughness further down the path (in a child ray created from BSDF sampling). In addition, using a cascading mechanism of flag values, we cull connections to caustic lights for this and children rays, which should be resolved through MNEE. This mechanism also cancels the MIS bsdf counter part at the casutic receiver depth, in essence leaving MNEE as the only sampling technique from receivers through refractive casters to caustic lights. This choice might not be optimal when the light gets large wrt to the receiver, though this is usually not when you want to use MNEE. This connection culling strategy removes a fair amount of fireflies, at the cost of introducing a slight bias. Because of the selective nature of the culling mechanism, reflective caustics still benefit from the native path regularization, which further removes fireflies on other surfaces (bouncing light off casters). Differential Revision: https://developer.blender.org/D13533
2022-04-01 15:44:24 +02:00
const int object_flags = intersection_get_object_flags(kg, &ss_isect.hits[0]);
const bool use_caustics = kernel_data.integrator.use_caustics &&
(object_flags & SD_OBJECT_CAUSTICS);
const bool use_raytrace_kernel = (shader_flags & SD_HAS_RAYTRACE);
Cycles: approximate shadow caustics using manifold next event estimation This adds support for selective rendering of caustics in shadows of refractive objects. Example uses are rendering of underwater caustics and eye caustics. This is based on "Manifold Next Event Estimation", a method developed for production rendering. The idea is to selectively enable shadow caustics on a few objects in the scene where they have a big visual impact, without impacting render performance for the rest of the scene. The Shadow Caustic option must be manually enabled on light, caustic receiver and caster objects. For such light paths, the Filter Glossy option will be ignored and replaced by sharp caustics. Currently this method has a various limitations: * Only caustics in shadows of refractive objects work, which means no caustics from reflection or caustics that outside shadows. Only up to 4 refractive caustic bounces are supported. * Caustic caster objects should have smooth normals. * Not currently support for Metal GPU rendering. In the future this method may be extended for more general caustics. TECHNICAL DETAILS This code adds manifold next event estimation through refractive surface(s) as a new sampling technique for direct lighting, i.e. finding the point on the refractive surface(s) along the path to a light sample, which satisfies Fermat's principle for a given microfacet normal and the path's end points. This technique involves walking on the "specular manifold" using a pseudo newton solver. Such a manifold is defined by the specular constraint matrix from the manifold exploration framework [2]. For each refractive interface, this constraint is defined by enforcing that the generalized half-vector projection onto the interface local tangent plane is null. The newton solver guides the walk by linearizing the manifold locally before reprojecting the linear solution onto the refractive surface. See paper [1] for more details about the technique itself and [3] for the half-vector light transport formulation, from which it is derived. [1] Manifold Next Event Estimation Johannes Hanika, Marc Droske, and Luca Fascione. 2015. Comput. Graph. Forum 34, 4 (July 2015), 87–97. https://jo.dreggn.org/home/2015_mnee.pdf [2] Manifold exploration: a Markov Chain Monte Carlo technique for rendering scenes with difficult specular transport Wenzel Jakob and Steve Marschner. 2012. ACM Trans. Graph. 31, 4, Article 58 (July 2012), 13 pages. https://www.cs.cornell.edu/projects/manifolds-sg12/ [3] The Natural-Constraint Representation of the Path Space for Efficient Light Transport Simulation. Anton S. Kaplanyan, Johannes Hanika, and Carsten Dachsbacher. 2014. ACM Trans. Graph. 33, 4, Article 102 (July 2014), 13 pages. https://cg.ivd.kit.edu/english/HSLT.php The code for this samping technique was inserted at the light sampling stage (direct lighting). If the walk is successful, it turns off path regularization using a specialized flag in the path state (PATH_MNEE_SUCCESS). This flag tells the integrator not to blur the brdf roughness further down the path (in a child ray created from BSDF sampling). In addition, using a cascading mechanism of flag values, we cull connections to caustic lights for this and children rays, which should be resolved through MNEE. This mechanism also cancels the MIS bsdf counter part at the casutic receiver depth, in essence leaving MNEE as the only sampling technique from receivers through refractive casters to caustic lights. This choice might not be optimal when the light gets large wrt to the receiver, though this is usually not when you want to use MNEE. This connection culling strategy removes a fair amount of fireflies, at the cost of introducing a slight bias. Because of the selective nature of the culling mechanism, reflective caustics still benefit from the native path regularization, which further removes fireflies on other surfaces (bouncing light off casters). Differential Revision: https://developer.blender.org/D13533
2022-04-01 15:44:24 +02:00
if (use_caustics) {
2022-07-15 13:08:51 +02:00
integrator_path_next_sorted(kg,
state,
DEVICE_KERNEL_INTEGRATOR_INTERSECT_SUBSURFACE,
DEVICE_KERNEL_INTEGRATOR_SHADE_SURFACE_MNEE,
shader);
}
else if (use_raytrace_kernel) {
2022-07-15 13:08:51 +02:00
integrator_path_next_sorted(kg,
state,
DEVICE_KERNEL_INTEGRATOR_INTERSECT_SUBSURFACE,
DEVICE_KERNEL_INTEGRATOR_SHADE_SURFACE_RAYTRACE,
shader);
}
else {
2022-07-15 13:08:51 +02:00
integrator_path_next_sorted(kg,
state,
DEVICE_KERNEL_INTEGRATOR_INTERSECT_SUBSURFACE,
DEVICE_KERNEL_INTEGRATOR_SHADE_SURFACE,
shader);
}
return true;
}
#endif /* __SUBSURFACE__ */
CCL_NAMESPACE_END