def parse_shape(node, material_dict, shape_id):
if node.attrib['type'] == 'obj' or node.attrib['type'] == 'serialized':
to_world = torch.eye(4)
serialized_shape_id = 0
mat_id = -1
light_intensity = None
filename = ''
for child in node:
if 'name' in child.attrib:
if child.attrib['name'] == 'filename':
filename = child.attrib['value']
elif child.attrib['name'] == 'toWorld':
to_world = parse_transform(child)
elif child.attrib['name'] == 'shapeIndex':
serialized_shape_id = int(child.attrib['value'])
if child.tag == 'ref':
mat_id = material_dict[child.attrib['id']]
elif child.tag == 'emitter':
for grandchild in child:
if grandchild.attrib['name'] == 'radiance':
light_intensity = parse_vector(
grandchild.attrib['value'])
if light_intensity.shape[0] == 1:
light_intensity = torch.tensor(\
[light_intensity[0],
light_intensity[0],
light_intensity[0]])
if node.attrib['type'] == 'obj':
vertices, indices, uvs, normals = pyredner.load_obj(filename)
else:
assert (node.attrib['type'] == 'serialized')
mitsuba_tri_mesh = redner.load_serialized(filename,
serialized_shape_id)
vertices = torch.from_numpy(mitsuba_tri_mesh.vertices)
indices = torch.from_numpy(mitsuba_tri_mesh.indices)
uvs = torch.from_numpy(mitsuba_tri_mesh.uvs)
normals = torch.from_numpy(mitsuba_tri_mesh.normals)
if uvs.shape[0] == 0:
uvs = None
if normals.shape[0] == 0:
normals = None
# Transform the vertices and normals
vertices = torch.cat((vertices, torch.ones(vertices.shape[0], 1)),
dim=1)
vertices = vertices @ torch.transpose(to_world, 0, 1)
vertices = vertices / vertices[:, 3:4]
vertices = vertices[:, 0:3].contiguous()
if normals is not None:
normals = normals @ (torch.inverse(torch.transpose(to_world, 0,
1))[:3, :3])
normals = normals.contiguous()
assert (vertices is not None)
assert (indices is not None)
lgt = None
if light_intensity is not None:
lgt = pyredner.Light(shape_id, light_intensity)
if pyredner.get_use_gpu():
# Copy to GPU
vertices = vertices.cuda()
indices = indices.cuda()
if uvs is not None:
uvs = uvs.cuda()
if normals is not None:
normals = normals.cuda()
return pyredner.Shape(vertices, indices, uvs, normals, mat_id), lgt
elif node.attrib['type'] == 'rectangle':
indices = torch.tensor([[0, 2, 1], [1, 2, 3]], dtype=torch.int32)
vertices = torch.tensor([[-1.0, -1.0, 0.0], [-1.0, 1.0, 0.0],
[1.0, -1.0, 0.0], [1.0, 1.0, 0.0]])
uvs = None
normals = None
to_world = torch.eye(4)
mat_id = -1
light_intensity = None
for child in node:
if 'name' in child.attrib:
if child.attrib['name'] == 'toWorld':
to_world = parse_transform(child)
if child.tag == 'ref':
mat_id = material_dict[child.attrib['id']]
elif child.tag == 'emitter':
for grandchild in child:
if grandchild.attrib['name'] == 'radiance':
light_intensity = parse_vector(
grandchild.attrib['value'])
if light_intensity.shape[0] == 1:
light_intensity = torch.tensor(\
[light_intensity[0],
light_intensity[0],
light_intensity[0]])
# Transform the vertices
# Transform the vertices and normals
vertices = torch.cat((vertices, torch.ones(vertices.shape[0], 1)),
dim=1)
vertices = vertices @ torch.transpose(to_world, 0, 1)
vertices = vertices / vertices[:, 3:4]
vertices = vertices[:, 0:3].contiguous()
if normals is not None:
normals = normals @ (torch.inverse(torch.transpose(to_world, 0,
1))[:3, :3])
normals = normals.contiguous()
assert (vertices is not None)
assert (indices is not None)
lgt = None
if light_intensity is not None:
lgt = pyrender.Light(shape_id, light_intensity)
if pyredner.get_use_gpu():
# Copy to GPU
vertices = vertices.cuda()
indices = indices.cuda()
if uvs is not None:
uvs = uvs.cuda()
if normals is not None:
normals = normals.cuda()
return shape.Shape(vertices, indices, uvs, normals, mat_id), lgt
else:
assert (False)
blocker_indices = torch.tensor([[0, 1, 2], [1, 3, 2]],
device=pyredner.get_device(),
dtype=torch.int32)
shape_blocker = pyredner.Shape(blocker_vertices, blocker_indices, None, None,
0)
light_vertices = torch.tensor(\
[[-0.1,15,-0.1],[-0.1,15,0.1],[0.1,15,-0.1],[0.1,15,0.1]],
device = pyredner.get_device())
light_indices = torch.tensor([[0, 2, 1], [1, 2, 3]],
device=pyredner.get_device(),
dtype=torch.int32)
shape_light = pyredner.Shape(light_vertices, light_indices, None, None, 1)
shapes = [shape_floor, shape_blocker, shape_light]
light_intensity = torch.tensor([5000.0, 5000.0, 5000.0])
# The first argument is the shape id of the light
light = pyredner.Light(2, light_intensity)
lights = [light]
scene = pyredner.Scene(cam, shapes, materials, lights)
args = pyredner.RenderFunction.serialize_scene(\
scene = scene,
num_samples = 256,
max_bounces = 1)
# Alias of the render function
render = pyredner.RenderFunction.apply
# Render our target
img = render(0, *args)
pyredner.imwrite(img.cpu(), 'results/test_shadow_camera/target.exr')
pyredner.imwrite(img.cpu(), 'results/test_shadow_camera/target.png')
target = pyredner.imread('results/test_shadow_camera/target.exr')
if pyredner.get_use_gpu():
[ 1.0, -1.0, -7.0],
[-1.0, 1.0, -7.0],
[ 1.0, 1.0, -7.0]], device = pyredner.get_device()),
indices = torch.tensor([[0, 1, 2],[1, 3, 2]],
dtype = torch.int32, device = pyredner.get_device()),
uvs = None,
normals = None,
material_id = 0)
# The shape list of the scene
shapes = [shape_triangle, shape_light]
# Now we assign some of the shapes in the scene as light sources.
# Again, all light sources in the scene are stored in a Python list.
# Each light is attached to a shape using shape id, additionally we need to
# assign the intensity of the light, which is a length 3 float tensor in CPU.
light = pyredner.Light(shape_id = 1,
intensity = torch.tensor([20.0,20.0,20.0]))
lights = [light]
# Finally we construct our scene using all the variables we setup previously.
scene = pyredner.Scene(cam, shapes, materials, lights)
# All PyTorch functions take a flat array of PyTorch tensors as input,
# therefore we need to serialize the scene into an array. The following
# function is doing this. We also specify how many Monte Carlo samples we want to
# use per pixel and the number of bounces for indirect illumination here
# (one bounce means only direct illumination).
scene_args = pyredner.RenderFunction.serialize_scene(\
scene = scene,
num_samples = 16,
max_bounces = 1)
# Render the scene as our target image.
# To render the scene, we use our custom PyTorch function in pyredner/render_pytorch.py
