mirror of
https://github.com/iperov/DeepFaceLab.git
synced 2025-08-19 13:09:56 -07:00
New rct added
This commit is contained in:
Cioscos
parent
3d7365a8e5
commit
deae2f19e9
4 changed files with 51 additions and 93 deletions
|
|
@ -1,4 +1,5 @@
|
|||
import cv2
|
||||
import numexpr as ne
|
||||
import numpy as np
|
||||
from numpy import linalg as npla
|
||||
import random
|
||||
|
|
@ -9,14 +10,12 @@ def color_transfer_sot(src,trg, steps=10, batch_size=5, reg_sigmaXY=16.0, reg_si
|
|||
"""
|
||||
Color Transform via Sliced Optimal Transfer
|
||||
ported by @iperov from https://github.com/dcoeurjo/OTColorTransfer
|
||||
|
||||
src - any float range any channel image
|
||||
dst - any float range any channel image, same shape as src
|
||||
steps - number of solver steps
|
||||
batch_size - solver batch size
|
||||
reg_sigmaXY - apply regularization and sigmaXY of filter, otherwise set to 0.0
|
||||
reg_sigmaV - sigmaV of filter
|
||||
|
||||
return value - clip it manually
|
||||
"""
|
||||
if not np.issubdtype(src.dtype, np.floating):
|
||||
|
|
@ -135,89 +134,53 @@ def color_transfer_idt(i0, i1, bins=256, n_rot=20):
|
|||
|
||||
return np.clip ( d0.T.reshape ( (h,w,c) ).astype(i0.dtype) , 0, 1)
|
||||
|
||||
def reinhard_color_transfer(target, source, clip=False, preserve_paper=False, source_mask=None, target_mask=None):
|
||||
"""
|
||||
Transfers the color distribution from the source to the target
|
||||
image using the mean and standard deviations of the L*a*b*
|
||||
color space.
|
||||
def reinhard_color_transfer(target : np.ndarray, source : np.ndarray, target_mask : np.ndarray = None, source_mask : np.ndarray = None, mask_cutoff=0.5) -> np.ndarray:
|
||||
"""
|
||||
Transfer color using rct method.
|
||||
target np.ndarray H W 3C (BGR) np.float32
|
||||
source np.ndarray H W 3C (BGR) np.float32
|
||||
target_mask(None) np.ndarray H W 1C np.float32
|
||||
source_mask(None) np.ndarray H W 1C np.float32
|
||||
|
||||
This implementation is (loosely) based on to the "Color Transfer
|
||||
between Images" paper by Reinhard et al., 2001.
|
||||
mask_cutoff(0.5) float
|
||||
masks are used to limit the space where color statistics will be computed to adjust the target
|
||||
reference: Color Transfer between Images https://www.cs.tau.ac.il/~turkel/imagepapers/ColorTransfer.pdf
|
||||
"""
|
||||
source = cv2.cvtColor(source, cv2.COLOR_BGR2LAB)
|
||||
target = cv2.cvtColor(target, cv2.COLOR_BGR2LAB)
|
||||
|
||||
Parameters:
|
||||
-------
|
||||
source: NumPy array
|
||||
OpenCV image in BGR color space (the source image)
|
||||
target: NumPy array
|
||||
OpenCV image in BGR color space (the target image)
|
||||
clip: Should components of L*a*b* image be scaled by np.clip before
|
||||
converting back to BGR color space?
|
||||
If False then components will be min-max scaled appropriately.
|
||||
Clipping will keep target image brightness truer to the input.
|
||||
Scaling will adjust image brightness to avoid washed out portions
|
||||
in the resulting color transfer that can be caused by clipping.
|
||||
preserve_paper: Should color transfer strictly follow methodology
|
||||
layed out in original paper? The method does not always produce
|
||||
aesthetically pleasing results.
|
||||
If False then L*a*b* components will scaled using the reciprocal of
|
||||
the scaling factor proposed in the paper. This method seems to produce
|
||||
more consistently aesthetically pleasing results
|
||||
source_input = source
|
||||
if source_mask is not None:
|
||||
source_input = source_input.copy()
|
||||
source_input[source_mask[...,0] < mask_cutoff] = [0,0,0]
|
||||
|
||||
Returns:
|
||||
-------
|
||||
transfer: NumPy array
|
||||
OpenCV image (w, h, 3) NumPy array (uint8)
|
||||
"""
|
||||
target_input = target
|
||||
if target_mask is not None:
|
||||
target_input = target_input.copy()
|
||||
target_input[target_mask[...,0] < mask_cutoff] = [0,0,0]
|
||||
|
||||
target_l_mean, target_l_std, target_a_mean, target_a_std, target_b_mean, target_b_std, \
|
||||
= target_input[...,0].mean(), target_input[...,0].std(), target_input[...,1].mean(), target_input[...,1].std(), target_input[...,2].mean(), target_input[...,2].std()
|
||||
|
||||
# convert the images from the RGB to L*ab* color space, being
|
||||
# sure to utilizing the floating point data type (note: OpenCV
|
||||
# expects floats to be 32-bit, so use that instead of 64-bit)
|
||||
source = cv2.cvtColor(source, cv2.COLOR_BGR2LAB).astype(np.float32)
|
||||
target = cv2.cvtColor(target, cv2.COLOR_BGR2LAB).astype(np.float32)
|
||||
source_l_mean, source_l_std, source_a_mean, source_a_std, source_b_mean, source_b_std, \
|
||||
= source_input[...,0].mean(), source_input[...,0].std(), source_input[...,1].mean(), source_input[...,1].std(), source_input[...,2].mean(), source_input[...,2].std()
|
||||
|
||||
# compute color statistics for the source and target images
|
||||
src_input = source if source_mask is None else source*source_mask
|
||||
tgt_input = target if target_mask is None else target*target_mask
|
||||
(lMeanSrc, lStdSrc, aMeanSrc, aStdSrc, bMeanSrc, bStdSrc) = lab_image_stats(src_input)
|
||||
(lMeanTar, lStdTar, aMeanTar, aStdTar, bMeanTar, bStdTar) = lab_image_stats(tgt_input)
|
||||
# not as in the paper: scale by the standard deviations using reciprocal of paper proposed factor
|
||||
target_l = target[...,0]
|
||||
target_l = ne.evaluate('(target_l - target_l_mean) * source_l_std / target_l_std + source_l_mean')
|
||||
|
||||
# subtract the means from the target image
|
||||
(l, a, b) = cv2.split(target)
|
||||
l -= lMeanTar
|
||||
a -= aMeanTar
|
||||
b -= bMeanTar
|
||||
target_a = target[...,1]
|
||||
target_a = ne.evaluate('(target_a - target_a_mean) * source_a_std / target_a_std + source_a_mean')
|
||||
|
||||
if preserve_paper:
|
||||
# scale by the standard deviations using paper proposed factor
|
||||
l = (lStdTar / lStdSrc) * l
|
||||
a = (aStdTar / aStdSrc) * a
|
||||
b = (bStdTar / bStdSrc) * b
|
||||
else:
|
||||
# scale by the standard deviations using reciprocal of paper proposed factor
|
||||
l = (lStdSrc / lStdTar) * l
|
||||
a = (aStdSrc / aStdTar) * a
|
||||
b = (bStdSrc / bStdTar) * b
|
||||
target_b = target[...,2]
|
||||
target_b = ne.evaluate('(target_b - target_b_mean) * source_b_std / target_b_std + source_b_mean')
|
||||
|
||||
# add in the source mean
|
||||
l += lMeanSrc
|
||||
a += aMeanSrc
|
||||
b += bMeanSrc
|
||||
np.clip(target_l, 0, 100, out=target_l)
|
||||
np.clip(target_a, -127, 127, out=target_a)
|
||||
np.clip(target_b, -127, 127, out=target_b)
|
||||
|
||||
# clip/scale the pixel intensities to [0, 255] if they fall
|
||||
# outside this range
|
||||
l = _scale_array(l, clip=clip)
|
||||
a = _scale_array(a, clip=clip)
|
||||
b = _scale_array(b, clip=clip)
|
||||
return cv2.cvtColor(np.stack([target_l,target_a,target_b], -1), cv2.COLOR_LAB2BGR)
|
||||
|
||||
# merge the channels together and convert back to the RGB color
|
||||
# space, being sure to utilize the 8-bit unsigned integer data
|
||||
# type
|
||||
transfer = cv2.merge([l, a, b])
|
||||
transfer = cv2.cvtColor(transfer.astype(np.uint8), cv2.COLOR_LAB2BGR)
|
||||
|
||||
# return the color transferred image
|
||||
return transfer
|
||||
|
||||
def linear_color_transfer(target_img, source_img, mode='pca', eps=1e-5):
|
||||
'''
|
||||
|
|
@ -355,9 +318,7 @@ def color_transfer(ct_mode, img_src, img_trg):
|
|||
if ct_mode == 'lct':
|
||||
out = linear_color_transfer (img_src, img_trg)
|
||||
elif ct_mode == 'rct':
|
||||
out = reinhard_color_transfer ( np.clip( img_src*255, 0, 255 ).astype(np.uint8),
|
||||
np.clip( img_trg*255, 0, 255 ).astype(np.uint8) )
|
||||
out = np.clip( out.astype(np.float32) / 255.0, 0.0, 1.0)
|
||||
out = reinhard_color_transfer(img_src, img_trg)
|
||||
elif ct_mode == 'mkl':
|
||||
out = color_transfer_mkl (img_src, img_trg)
|
||||
elif ct_mode == 'idt':
|
||||
|
|
@ -381,7 +342,6 @@ def color_augmentation(img, seed=None):
|
|||
img[:, :, :3] = face
|
||||
return (face / 255.0).astype(np.float32)
|
||||
|
||||
|
||||
def random_lab_rotation(image, seed=None):
|
||||
"""
|
||||
Randomly rotates image color around the L axis in LAB colorspace,
|
||||
|
|
@ -400,7 +360,6 @@ def random_lab_rotation(image, seed=None):
|
|||
np.clip(image, 0, 1, out=image)
|
||||
return image
|
||||
|
||||
|
||||
def random_lab(image, seed=None):
|
||||
""" Perform random color/lightness adjustment in L*a*b* colorspace """
|
||||
random.seed(seed)
|
||||
|
|
|
|||
|
|
@ -170,10 +170,7 @@ def MergeMaskedFace (predictor_func, predictor_input_shape,
|
|||
|
||||
if 'seamless' not in cfg.mode and cfg.color_transfer_mode != 0:
|
||||
if cfg.color_transfer_mode == 1: #rct
|
||||
prd_face_bgr = imagelib.reinhard_color_transfer ( np.clip( prd_face_bgr*wrk_face_mask_area_a*255, 0, 255).astype(np.uint8),
|
||||
np.clip( dst_face_bgr*wrk_face_mask_area_a*255, 0, 255).astype(np.uint8), )
|
||||
|
||||
prd_face_bgr = np.clip( prd_face_bgr.astype(np.float32) / 255.0, 0.0, 1.0)
|
||||
prd_face_bgr = imagelib.reinhard_color_transfer ( prd_face_bgr*wrk_face_mask_area_a, dst_face_bgr*wrk_face_mask_area_a )
|
||||
elif cfg.color_transfer_mode == 2: #lct
|
||||
prd_face_bgr = imagelib.linear_color_transfer (prd_face_bgr, dst_face_bgr)
|
||||
elif cfg.color_transfer_mode == 3: #mkl
|
||||
|
|
@ -252,9 +249,7 @@ def MergeMaskedFace (predictor_func, predictor_input_shape,
|
|||
|
||||
if 'seamless' in cfg.mode and cfg.color_transfer_mode != 0:
|
||||
if cfg.color_transfer_mode == 1:
|
||||
out_face_bgr = imagelib.reinhard_color_transfer ( np.clip(out_face_bgr*wrk_face_mask_area_a*255, 0, 255).astype(np.uint8),
|
||||
np.clip(dst_face_bgr*wrk_face_mask_area_a*255, 0, 255).astype(np.uint8) )
|
||||
out_face_bgr = np.clip( out_face_bgr.astype(np.float32) / 255.0, 0.0, 1.0)
|
||||
out_face_bgr = imagelib.reinhard_color_transfer (out_face_bgr*wrk_face_mask_area_a, dst_face_bgr*wrk_face_mask_area_a)
|
||||
elif cfg.color_transfer_mode == 2: #lct
|
||||
out_face_bgr = imagelib.linear_color_transfer (out_face_bgr, dst_face_bgr)
|
||||
elif cfg.color_transfer_mode == 3: #mkl
|
||||
|
|
|
|||
|
|
@ -1,5 +1,6 @@
|
|||
tqdm
|
||||
numpy==1.19.3
|
||||
numexpr
|
||||
h5py==2.10.0
|
||||
opencv-python==4.1.0.25
|
||||
ffmpeg-python==0.1.17
|
||||
|
|
@ -7,3 +8,4 @@ scikit-image==0.14.2
|
|||
scipy==1.4.1
|
||||
colorama
|
||||
tensorflow-gpu==2.4.0
|
||||
tf2onnx==1.8.4
|
||||
|
|
@ -1,5 +1,6 @@
|
|||
tqdm
|
||||
numpy==1.19.3
|
||||
numexpr
|
||||
h5py==2.10.0
|
||||
opencv-python==4.1.0.25
|
||||
ffmpeg-python==0.1.17
|
||||
|
|
@ -8,5 +9,6 @@ scipy==1.4.1
|
|||
colorama
|
||||
tensorflow-gpu==2.4.0
|
||||
pyqt5
|
||||
tf2onnx==1.8.4
|
||||
Flask==1.1.1
|
||||
flask-socketio==4.2.1
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue