图片动漫化 - 面部 - AnimeGAN

图片处理

#!/usr/bin/env python
# coding: utf-8

import torch 
from PIL import Image

import os
import dlib
import collections
from typing import Union, List
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt

import PIL.Image
import PIL.ImageFile
import numpy as np
import scipy.ndimage

def get_dlib_face_detector(predictor_path: str = "shape_predictor_68_face_landmarks.dat"):

    detector = dlib.get_frontal_face_detector()
    shape_predictor = dlib.shape_predictor(predictor_path)

    def detect_face_landmarks(img: Union[Image.Image, np.ndarray]):
        if isinstance(img, Image.Image):
            img = np.array(img)
        faces = []
        dets = detector(img)
        for d in dets:
            shape = shape_predictor(img, d)
            faces.append(np.array([[v.x, v.y] for v in shape.parts()]))
        return faces
    
    return detect_face_landmarks

def align_and_crop_face(
    img: Image.Image,
    landmarks: np.ndarray,
    expand: float = 1.0,
    output_size: int = 1024, 
    transform_size: int = 4096,
    enable_padding: bool = True,):
    # Parse landmarks.
    # pylint: disable=unused-variable
    lm = landmarks
    lm_chin          = lm[0  : 17]  # left-right
    lm_eyebrow_left  = lm[17 : 22]  # left-right
    lm_eyebrow_right = lm[22 : 27]  # left-right
    lm_nose          = lm[27 : 31]  # top-down
    lm_nostrils      = lm[31 : 36]  # top-down
    lm_eye_left      = lm[36 : 42]  # left-clockwise
    lm_eye_right     = lm[42 : 48]  # left-clockwise
    lm_mouth_outer   = lm[48 : 60]  # left-clockwise
    lm_mouth_inner   = lm[60 : 68]  # left-clockwise

    # Calculate auxiliary vectors.
    eye_left     = np.mean(lm_eye_left, axis=0)
    eye_right    = np.mean(lm_eye_right, axis=0)
    eye_avg      = (eye_left + eye_right) * 0.5
    eye_to_eye   = eye_right - eye_left
    mouth_left   = lm_mouth_outer[0]
    mouth_right  = lm_mouth_outer[6]
    mouth_avg    = (mouth_left + mouth_right) * 0.5
    eye_to_mouth = mouth_avg - eye_avg

    # Choose oriented crop rectangle.
    x = eye_to_eye - np.flipud(eye_to_mouth) * [-1, 1]
    x /= np.hypot(*x)
    x *= max(np.hypot(*eye_to_eye) * 2.0, np.hypot(*eye_to_mouth) * 1.8)
    x *= expand
    y = np.flipud(x) * [-1, 1]
    c = eye_avg + eye_to_mouth * 0.1
    quad = np.stack([c - x - y, c - x + y, c + x + y, c + x - y])
    qsize = np.hypot(*x) * 2

    # Shrink.
    shrink = int(np.floor(qsize / output_size * 0.5))
    if shrink > 1:
        rsize = (int(np.rint(float(img.size[0]) / shrink)), int(np.rint(float(img.size[1]) / shrink)))
        img = img.resize(rsize, PIL.Image.ANTIALIAS)
        quad /= shrink
        qsize /= shrink

    # Crop.
    border = max(int(np.rint(qsize * 0.1)), 3)
    crop = (int(np.floor(min(quad[:,0]))), int(np.floor(min(quad[:,1]))), int(np.ceil(max(quad[:,0]))), int(np.ceil(max(quad[:,1]))))
    crop = (max(crop[0] - border, 0), max(crop[1] - border, 0), min(crop[2] + border, img.size[0]), min(crop[3] + border, img.size[1]))
    if crop[2] - crop[0] < img.size[0] or crop[3] - crop[1] < img.size[1]:
        img = img.crop(crop)
        quad -= crop[0:2]

    # Pad.
    pad = (int(np.floor(min(quad[:,0]))), int(np.floor(min(quad[:,1]))), int(np.ceil(max(quad[:,0]))), int(np.ceil(max(quad[:,1]))))
    pad = (max(-pad[0] + border, 0), max(-pad[1] + border, 0), max(pad[2] - img.size[0] + border, 0), max(pad[3] - img.size[1] + border, 0))
    if enable_padding and max(pad) > border - 4:
        pad = np.maximum(pad, int(np.rint(qsize * 0.3)))
        img = np.pad(np.float32(img), ((pad[1], pad[3]), (pad[0], pad[2]), (0, 0)), 'reflect')
        h, w, _ = img.shape
        y, x, _ = np.ogrid[:h, :w, :1]
        mask = np.maximum(1.0 - np.minimum(np.float32(x) / pad[0], np.float32(w-1-x) / pad[2]), 1.0 - np.minimum(np.float32(y) / pad[1], np.float32(h-1-y) / pad[3]))
        blur = qsize * 0.02
        img += (scipy.ndimage.gaussian_filter(img, [blur, blur, 0]) - img) * np.clip(mask * 3.0 + 1.0, 0.0, 1.0)
        img += (np.median(img, axis=(0,1)) - img) * np.clip(mask, 0.0, 1.0)
        img = PIL.Image.fromarray(np.uint8(np.clip(np.rint(img), 0, 255)), 'RGB')
        quad += pad[:2]

    # Transform.
    img = img.transform((transform_size, transform_size), PIL.Image.QUAD, (quad + 0.5).flatten(), PIL.Image.BILINEAR)
    if output_size < transform_size:
        img = img.resize((output_size, output_size), PIL.Image.ANTIALIAS)

    return img

图片测试

# 加载模型和面部检测
device = "cuda" if torch.cuda.is_available() else "cpu"
model = torch.hub.load("bryandlee/animegan2-pytorch:main", "generator", device=device).eval()
face2paint = torch.hub.load("bryandlee/animegan2-pytorch:main", "face2paint", device=device, side_by_side=True)
face_detector = get_dlib_face_detector()

# 加载图片并动漫化
img = Image.open("1.jpeg").convert("RGB")
landmarks = face_detector(img)
for landmark in landmarks:
	face = align_and_crop_face(img, landmark, expand=1.3)
	plt.imshow(face2paint(model=model, img=face, size=512))
	plt.axis('off')
	plt.show()

结果

1.jpeg

 输出