GoodCodes: FFHQ/CelebA数据与处理——人脸图像对齐

这是一段 StyleGAN(v2) 使用的人脸图像对齐代码，也可用于其他任务和其他人脸数据集的对齐。

import numpy as np 
from PIL import Image 
from tqdm import tqdm
import os
import json
import matplotlib.pyplot as plt 
import scipy 
import scipy.ndimage

## 全局变量
output_size = 256
transform_size = 256

def align_face(img, landmarks, enable_padding=True):
    '''
    Input(s):
        `img` --type=PIL.Image.Object --mode='RGB'
        `landmarks` --type=list --shape=(5,2) 
                    --content=[[x_left_eye_center, y_left_eye_center],
                               [x_right_eye_center, y_right_eye_center],
                               [x_nose, y_nose],
                               [x_left_mouth_corner, y_left_mouth_corner],
                               [x_right_mouth_corner, y_right_mouth_corner]]]
    Return(s):
        `img` --description="aligned_img" --type=PIL.Image.Object 
              --mode='RGB' --size=transform_size x transform_size 
    '''
    # Calculate auxiliary vectors.
    eye_left = np.array(landmarks[0])
    eye_right = np.array(landmarks[1])
    eye_avg = (eye_left+eye_right)*0.5
    eye_to_eye = eye_right - eye_left

    mouth_left = np.array(landmarks[3])
    mouth_right = np.array(landmarks[4])
    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)
    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, 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 = Image.fromarray(np.uint8(np.clip(np.rint(img), 0, 255)), 'RGB')
        quad += pad[:2]

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

    # Save aligned image.
    return img