def growing(self,
mesh: MeshInference,
start: int,
end: int,
num_frames: int,
zero_places: NoiseT = ()) -> factory.Noise:
export_name = f'{self.opt.cp_folder}/inference/{mesh.mesh_name}/scene00'
start, end = self.trim(start, end)
if len(zero_places) == 1:
zero_places = zero_places * (end - start + 1)
z = self.get_z_sequence(mesh, end - start)
for i in range(min(len(z), len(zero_places))):
if zero_places[i]:
z[i] = 0
deltas = self.generator.grow_forward(mesh.copy(), z, end, start)
mesh.export(f'{export_name}/{0:02d}')
for i in range(end - start + 1):
base_vs, cur_delta = mesh.vs.clone(), deltas[i]
for j in range(num_frames):
mesh.vs = base_vs + cur_delta * (j + 1) / num_frames
mesh.export(f'{export_name}/{(num_frames * i + j + 1):02d}')
print(
f'done: {num_frames * i + j + 1}/{num_frames * (end - start + 1)}'
)
if i < end - start:
mesh.upsample()
return z
def grow_forward(self, m: MeshInference, z: List[Union[T, float]],
level: int, start_level: int) -> TS:
def grow_level(z_, level_) -> T:
nonlocal m
features = m(z_, self.opt.noise_before)
out = self.levels[level_](features, m.gfmm)
m, displacement = m.grow_add(out)
return displacement
displacements: TS = []
with torch.no_grad():
for j, i in enumerate(range(start_level, level)):
displacements.append(grow_level(z[j], i))
m = m.upsample()
displacements.append(grow_level(z[-1], level))
return displacements