有没有人知道任何Tensorflow代码用于不失真的图像？ （去除鱼眼效果）
目前，我正在使用OpenCV进行无损图像处理。但是，我想在网络中推送该代码。这样做是否有开源代码或Tensorflow功能？我无法通过谷歌找到任何东西。
干得好。我攻击了spatial_transformer代码。我想你必须在运行这段代码之前将这些点乘以K ^ -1（逆相机矩阵），然后如果你的相机矩阵不是标识相机矩阵，则将它们乘以K.
def distort(images, d, name='distort'):
def _repeat(x, n_repeats):
with tf.variable_scope('_repeat'):
rep = tf.transpose(
tf.expand_dims(tf.ones(shape=tf.stack([n_repeats, ])), 1), [1, 0])
rep = tf.cast(rep, 'int32')
x = tf.matmul(tf.reshape(x, (-1, 1)), rep)
return tf.reshape(x, [-1])
def _interpolate(im, x, y, out_size):
with tf.variable_scope('_interpolate'):
# constants
num_batch = tf.shape(im)[0]
height = tf.shape(im)[1]
width = tf.shape(im)[2]
channels = tf.shape(im)[3]
x = tf.cast(x, 'float32')
y = tf.cast(y, 'float32')
height_f = tf.cast(height, 'float32')
width_f = tf.cast(width, 'float32')
out_height = out_size[0]
out_width = out_size[1]
zero = tf.zeros([], dtype='int32')
max_y = tf.cast(tf.shape(im)[1] - 1, 'int32')
max_x = tf.cast(tf.shape(im)[2] - 1, 'int32')
# scale indices from [-1, 1] to [0, width/height]
x = (x + 1.0)*(width_f) / 2.0
y = (y + 1.0)*(height_f) / 2.0
# do sampling
x0 = tf.cast(tf.floor(x), 'int32')
x1 = x0 + 1
y0 = tf.cast(tf.floor(y), 'int32')
y1 = y0 + 1
x0 = tf.clip_by_value(x0, zero, max_x)
x1 = tf.clip_by_value(x1, zero, max_x)
y0 = tf.clip_by_value(y0, zero, max_y)
y1 = tf.clip_by_value(y1, zero, max_y)
dim2 = width
dim1 = width*height
base = _repeat(tf.range(num_batch)*dim1, out_height*out_width)
base_y0 = base + y0*dim2
base_y1 = base + y1*dim2
idx_a = base_y0 + x0
idx_b = base_y1 + x0
idx_c = base_y0 + x1
idx_d = base_y1 + x1
# use indices to lookup pixels in the flat image and restore
# channels dim
im_flat = tf.reshape(im, tf.stack([-1, channels]))
im_flat = tf.cast(im_flat, 'float32')
Ia = tf.gather(im_flat, idx_a)
Ib = tf.gather(im_flat, idx_b)
Ic = tf.gather(im_flat, idx_c)
Id = tf.gather(im_flat, idx_d)
# and finally calculate interpolated values
x0_f = tf.cast(x0, 'float32')
x1_f = tf.cast(x1, 'float32')
y0_f = tf.cast(y0, 'float32')
y1_f = tf.cast(y1, 'float32')
wa = tf.expand_dims(((x1_f-x) * (y1_f-y)), 1)
wb = tf.expand_dims(((x1_f-x) * (y-y0_f)), 1)
wc = tf.expand_dims(((x-x0_f) * (y1_f-y)), 1)
wd = tf.expand_dims(((x-x0_f) * (y-y0_f)), 1)
output = tf.add_n([wa*Ia, wb*Ib, wc*Ic, wd*Id])
return output
def _transform(images, d, out_size):
with tf.variable_scope('_transform'):
shape = tf.shape(images)
num_batch = tf.shape(images)[0]
num_channels = images.get_shape()[3]
out_width = out_size[1]
out_height = out_size[0]
cx = fx = fy = tf.to_float(out_width) / 2
cy = tf.to_float(out_height) / 2
x = tf.linspace(-1., 1., out_width)
y = tf.linspace(-1., 1., out_height)
x, y = tf.meshgrid(x, y)
x = tf.tile(tf.reshape(x, [1, -1, 1]), [num_batch,1,1])
y = tf.tile(tf.reshape(y, [1, -1, 1]), [num_batch,1,1])
a = x
b = y
r2 = tf.square(a) + tf.square(b)
r = tf.sqrt(r2)
r = tf.Print(r, [tf.reduce_min(r), tf.reduce_max(r)], "R min/max: ")
theta = tf.atan(r)
theta_d = theta*(1.0 + tf.reduce_sum(tf.reshape(d,
[1,1,4]) * tf.concat([tf.square(theta),
tf.pow(theta, 4), tf.pow(theta, 6), tf.pow(theta,
8)], axis=-1),
axis=-1, keepdims=True))
tdr = theta_d / r
xd = a * tdr
yd = b * tdr
xd = tf.reshape(xd, [-1])
yd = tf.reshape(yd, [-1])
input_transformed = _interpolate(
images, xd, yd,
out_size)
output = tf.reshape(input_transformed,
tf.stack([num_batch, out_height, out_width,
num_channels]))
return output
with tf.variable_scope(name):
output = _transform(images, d, tf.shape(images)[1:3])
return output