Spaces:
Running
Running
File size: 5,093 Bytes
7088d16 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 |
#!/usr/bin/env python3
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the BSD-style license found in the
# LICENSE file in the root directory of this source tree.
"""
This example demonstrates scene optimization with the plain
pulsar interface. For this, a reference image has been pre-generated
(you can find it at `../../tests/pulsar/reference/examples_TestRenderer_test_smallopt.png`).
The scene is initialized with random spheres. Gradient-based
optimization is used to converge towards a faithful
scene representation.
"""
import logging
import math
import cv2
import imageio
import numpy as np
import torch
from pytorch3d.renderer.points.pulsar import Renderer
from torch import nn, optim
LOGGER = logging.getLogger(__name__)
N_POINTS = 10_000
WIDTH = 1_000
HEIGHT = 1_000
DEVICE = torch.device("cuda")
class SceneModel(nn.Module):
"""
A simple scene model to demonstrate use of pulsar in PyTorch modules.
The scene model is parameterized with sphere locations (vert_pos),
channel content (vert_col), radiuses (vert_rad), camera position (cam_pos),
camera rotation (cam_rot) and sensor focal length and width (cam_sensor).
The forward method of the model renders this scene description. Any
of these parameters could instead be passed as inputs to the forward
method and come from a different model.
"""
def __init__(self):
super(SceneModel, self).__init__()
self.gamma = 1.0
# Points.
torch.manual_seed(1)
vert_pos = torch.rand(N_POINTS, 3, dtype=torch.float32) * 10.0
vert_pos[:, 2] += 25.0
vert_pos[:, :2] -= 5.0
self.register_parameter("vert_pos", nn.Parameter(vert_pos, requires_grad=True))
self.register_parameter(
"vert_col",
nn.Parameter(
torch.ones(N_POINTS, 3, dtype=torch.float32) * 0.5, requires_grad=True
),
)
self.register_parameter(
"vert_rad",
nn.Parameter(
torch.ones(N_POINTS, dtype=torch.float32) * 0.3, requires_grad=True
),
)
self.register_buffer(
"cam_params",
torch.tensor(
[0.0, 0.0, 0.0, 0.0, math.pi, 0.0, 5.0, 2.0], dtype=torch.float32
),
)
# The volumetric optimization works better with a higher number of tracked
# intersections per ray.
self.renderer = Renderer(
WIDTH, HEIGHT, N_POINTS, n_track=32, right_handed_system=True
)
def forward(self):
return self.renderer.forward(
self.vert_pos,
self.vert_col,
self.vert_rad,
self.cam_params,
self.gamma,
45.0,
return_forward_info=True,
)
def cli():
"""
Scene optimization example using pulsar.
"""
LOGGER.info("Loading reference...")
# Load reference.
ref = (
torch.from_numpy(
imageio.imread(
"../../tests/pulsar/reference/examples_TestRenderer_test_smallopt.png"
)[:, ::-1, :].copy()
).to(torch.float32)
/ 255.0
).to(DEVICE)
# Set up model.
model = SceneModel().to(DEVICE)
# Optimizer.
optimizer = optim.SGD(
[
{"params": [model.vert_col], "lr": 1e0},
{"params": [model.vert_rad], "lr": 5e-3},
{"params": [model.vert_pos], "lr": 1e-2},
]
)
LOGGER.info("Optimizing...")
# Optimize.
for i in range(500):
optimizer.zero_grad()
result, result_info = model()
# Visualize.
result_im = (result.cpu().detach().numpy() * 255).astype(np.uint8)
cv2.imshow("opt", result_im[:, :, ::-1])
overlay_img = np.ascontiguousarray(
((result * 0.5 + ref * 0.5).cpu().detach().numpy() * 255).astype(np.uint8)[
:, :, ::-1
]
)
overlay_img = cv2.putText(
overlay_img,
"Step %d" % (i),
(10, 40),
cv2.FONT_HERSHEY_SIMPLEX,
1,
(0, 0, 0),
2,
cv2.LINE_AA,
False,
)
cv2.imshow("overlay", overlay_img)
cv2.waitKey(1)
# Update.
loss = ((result - ref) ** 2).sum()
LOGGER.info("loss %d: %f", i, loss.item())
loss.backward()
optimizer.step()
# Cleanup.
with torch.no_grad():
model.vert_col.data = torch.clamp(model.vert_col.data, 0.0, 1.0)
# Remove points.
model.vert_pos.data[model.vert_rad < 0.001, :] = -1000.0
model.vert_rad.data[model.vert_rad < 0.001] = 0.0001
vd = (
(model.vert_col - torch.ones(3, dtype=torch.float32).to(DEVICE))
.abs()
.sum(dim=1)
)
model.vert_pos.data[vd <= 0.2] = -1000.0
LOGGER.info("Done.")
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO)
cli()
|