1. 程式人生 > >用深度神經網路搭建馬賽克神器,高清無碼效果感人

用深度神經網路搭建馬賽克神器,高清無碼效果感人

目錄

專案背景

適用範圍

使用方法


  • 專案背景

相信一提起馬賽克這個東西,不少小夥伴都痛心疾首,雖然最近幾年也頻繁傳出有在研發去除馬賽克的軟體,一直沒有成品問世。不過最近一位程式設計師及經過不斷努力終於完成了這款軟體。

據悉這位程式設計師“deeppomf”用深度神經網路開發出了一個能抹去馬賽克讓原圖重現的神奇程式:DeepCreamPy 。為了使這款軟體達到更好的效果,作者在短短几個月內收集了超過10萬張未打碼的原圖,但其中95%的圖片他都沒有仔細看過,只因為太過於浪費時間了。軟體被上傳分享後,在一週內被下載了500多次。不過目前該軟體的侷限性還很大,只能完成一些簡單的修復。

該專案使用深度完全卷積神經網路(deep fully convolutional neural network),參照了英偉達在今年4月前釋出的一篇論文。當然,英偉達原文的目的可不是用來做羞羞的事情,而是為了復原畫面被單色條帶遮擋的問題。

從實際效果來看,復原後的圖片塗抹痕跡仍然比較明顯,不過處理線條比較簡單的漫畫可以說是綽綽有餘。 

  • 適用範圍

DeepCreamPy僅適用於薄碼,如果馬賽克太大太厚,去碼可能會失效。另外,它對真人圖片無效。如果你非要嘗試,可以看一下強行使用的效果:

而且DeepCreamPy目前的版本還不能完全自動處理圖片,需要用Photoshop首先對馬賽克部分進行手動預處理。 

  • 使用方法

第一步:安裝程式

1、如果你是64位Windows使用者,恭喜你可以直接下載exe程式

下載地址

https://github.com/deeppomf/DeepCreamPy/releases/latest

2、否則需要自己編譯,編譯程式碼需要一下元件:

Python 3.6

TensorFlow 1.10

Keras 2.2.4

Pillow

h5py

請注意軟體版本,Windows上的TensorFlow不相容Python 2,也不相容Python 3.7。

程式碼如下:

import numpy as np
from PIL import Image
import os

from copy import deepcopy

import config
from libs.pconv_hybrid_model import PConvUnet
from libs.utils import *

class Decensor:

    def __init__(self):
        self.args = config.get_args()
        self.is_mosaic = self.args.is_mosaic

        self.mask_color = [self.args.mask_color_red/255.0, self.args.mask_color_green/255.0, self.args.mask_color_blue/255.0]

        if not os.path.exists(self.args.decensor_output_path):
            os.makedirs(self.args.decensor_output_path)

        self.load_model()

    def get_mask(self, colored):
        mask = np.ones(colored.shape, np.uint8)
        i, j = np.where(np.all(colored[0] == self.mask_color, axis=-1))
        mask[0, i, j] = 0
        return mask

    def load_model(self):
        self.model = PConvUnet()
        self.model.load(
            r"./models/model.h5",
            train_bn=False,
            lr=0.00005
        )

    def decensor_all_images_in_folder(self):
        #load model once at beginning and reuse same model
        #self.load_model()
        color_dir = self.args.decensor_input_path
        file_names = os.listdir(color_dir)

        #convert all images into np arrays and put them in a list
        for file_name in file_names:
            color_file_path = os.path.join(color_dir, file_name)
            color_bn, color_ext = os.path.splitext(file_name)
            if os.path.isfile(color_file_path) and color_ext.casefold() == ".png":
                print("--------------------------------------------------------------------------")
                print("Decensoring the image {}".format(color_file_path))
                colored_img = Image.open(color_file_path)
                #if we are doing a mosaic decensor
                if self.is_mosaic:
                    #get the original file that hasn't been colored
                    ori_dir = self.args.decensor_input_original_path
                    #since the original image might not be a png, test multiple file formats
                    valid_formats = {".png", ".jpg", ".jpeg"}
                    for test_file_name in os.listdir(ori_dir):
                        test_bn, test_ext = os.path.splitext(test_file_name)
                        if (test_bn == color_bn) and (test_ext.casefold() in valid_formats):
                            ori_file_path = os.path.join(ori_dir, test_file_name)
                            ori_img = Image.open(ori_file_path)
                            # colored_img.show()
                            self.decensor_image(ori_img, colored_img, file_name)
                            break
                    else: #for...else, i.e if the loop finished without encountering break
                        print("Corresponding original, uncolored image not found in {}.".format(ori_file_path))
                        print("Check if it exists and is in the PNG or JPG format.")
                else:
                    self.decensor_image(colored_img, colored_img, file_name)
        print("--------------------------------------------------------------------------")

    #decensors one image at a time
    #TODO: decensor all cropped parts of the same image in a batch (then i need input for colored an array of those images and make additional changes)
    def decensor_image(self, ori, colored, file_name):
        width, height = ori.size
        #save the alpha channel if the image has an alpha channel
        has_alpha = False
        if (ori.mode == "RGBA"):
            has_alpha = True
            alpha_channel = np.asarray(ori)[:,:,3]
            alpha_channel = np.expand_dims(alpha_channel, axis =-1)
            ori = ori.convert('RGB')

        ori_array = image_to_array(ori)
        ori_array = np.expand_dims(ori_array, axis = 0)

        if self.is_mosaic:
            #if mosaic decensor, mask is empty
            # mask = np.ones(ori_array.shape, np.uint8)
            # print(mask.shape)
            colored = colored.convert('RGB')
            color_array = image_to_array(colored)
            color_array = np.expand_dims(color_array, axis = 0)
            mask = self.get_mask(color_array)
            # mask_reshaped = mask[0,:,:,:] * 255.0
            # mask_img = Image.fromarray(mask_reshaped.astype('uint8'))
            # mask_img.show()

        else:
            mask = self.get_mask(ori_array)

        #colored image is only used for finding the regions
        regions = find_regions(colored.convert('RGB'))
        print("Found {region_count} censored regions in this image!".format(region_count = len(regions)))

        if len(regions) == 0 and not self.is_mosaic:
            print("No green regions detected!")
            return

        output_img_array = ori_array[0].copy()

        for region_counter, region in enumerate(regions, 1):
            bounding_box = expand_bounding(ori, region)
            crop_img = ori.crop(bounding_box)
            # crop_img.show()
            #convert mask back to image
            mask_reshaped = mask[0,:,:,:] * 255.0
            mask_img = Image.fromarray(mask_reshaped.astype('uint8'))
            #resize the cropped images
            crop_img = crop_img.resize((512, 512))
            crop_img_array = image_to_array(crop_img)
            crop_img_array = np.expand_dims(crop_img_array, axis = 0)
            #resize the mask images
            mask_img = mask_img.crop(bounding_box)
            mask_img = mask_img.resize((512, 512))
            # mask_img.show()
            #convert mask_img back to array 
            mask_array = image_to_array(mask_img)
            #the mask has been upscaled so there will be values not equal to 0 or 1

            mask_array[mask_array > 0] = 1
            
            if self.is_mosaic:
                a, b = np.where(np.all(mask_array == 0, axis = -1))
                print(a, b)
                coords = [coord for coord in zip(a,b) if ((coord[0] + coord[1]) % 2 == 0)]
                a,b = zip(*coords)

                mask_array[a,b] = 1
                # mask_array = mask_array * 255.0
                # img = Image.fromarray(mask_array.astype('uint8'))
                # img.show()
                # return

            mask_array = np.expand_dims(mask_array, axis = 0)

            # Run predictions for this batch of images
            pred_img_array = self.model.predict([crop_img_array, mask_array, mask_array])
            
            pred_img_array = pred_img_array * 255.0
            pred_img_array = np.squeeze(pred_img_array, axis = 0)

            #scale prediction image back to original size
            bounding_width = bounding_box[2]-bounding_box[0]
            bounding_height = bounding_box[3]-bounding_box[1]
            #convert np array to image

            # print(bounding_width,bounding_height)
            # print(pred_img_array.shape)

            pred_img = Image.fromarray(pred_img_array.astype('uint8'))
            # pred_img.show()
            pred_img = pred_img.resize((bounding_width, bounding_height), resample = Image.BICUBIC)

            pred_img_array = image_to_array(pred_img)

            # print(pred_img_array.shape)
            pred_img_array = np.expand_dims(pred_img_array, axis = 0)

            # copy the decensored regions into the output image
            for i in range(len(ori_array)):
                for col in range(bounding_width):
                    for row in range(bounding_height):
                        bounding_width_index = col + bounding_box[0]
                        bounding_height_index = row + bounding_box[1]
                        if (bounding_width_index, bounding_height_index) in region:
                            output_img_array[bounding_height_index][bounding_width_index] = pred_img_array[i,:,:,:][row][col]
            print("{region_counter} out of {region_count} regions decensored.".format(region_counter=region_counter, region_count=len(regions)))

        output_img_array = output_img_array * 255.0

        #restore the alpha channel if the image had one
        if has_alpha:
            output_img_array = np.concatenate((output_img_array, alpha_channel), axis = 2)

        output_img = Image.fromarray(output_img_array.astype('uint8'))

        #save the decensored image
        #file_name, _ = os.path.splitext(file_name)
        save_path = os.path.join(self.args.decensor_output_path, file_name)
        output_img.save(save_path)

        print("Decensored image saved to {save_path}!".format(save_path=save_path))
        return

if __name__ == '__main__':
    decensor = Decensor()
    decensor.decensor_all_images_in_folder()

注意:執行Demo需要翻牆下載模型,這裡為了方便小夥伴,我已經下載完畢:https://download.csdn.net/download/m0_38106923/10798221

第二步:手動處理黑條遮擋和馬賽克遮擋

首先開啟Photoshop或者其它圖片處理器。對於單色條遮住人物敏感部位的情況,使用純綠色(色號#00FF00#)預處理圖片,以綠條取代圖片中的黑條。

強烈建議使用鉛筆而不是毛刷工具,如果使用毛刷,請一定要關閉抗鋸齒功能。或者用魔棒選中馬賽克區域,再用油漆桶上色。這裡我給各位分享一個Python編寫的處理工具,程式碼比較長,所以和模型檔案放在一起,各位可以嘗試下載。

最後將處理的檔案以PNG格式儲存在軟體的”decensor_input”資料夾中。如果敏感部位不是黑條,而是馬賽克,還需要將未上色的原始圖片放入”decensor_input_original” 資料夾中,並確保其檔名和放在”decensor_input”中的預處理圖片檔名相同

第三步:執行去馬賽克軟體

1、64位Windows使用者下載程式的exe後,雙擊軟體即可

2、自行編譯專案的使用者,需要執行以下兩個命令

對於黑條遮擋的圖片,輸入以下命令:

$ pythondecensor.py

對於馬賽克遮擋的圖片,輸入以下命令:

$ python decensor.py —is_mosaic=True

注意事項

如果你圖片處理後成了這樣:

一定是你處理的姿勢不對,請注意不要犯以下兩種錯誤:

第一幅圖中,圖片馬賽克區域沒有完全塗滿;第二幅圖中,由於開啟了抗鋸齒功能,導致馬賽克邊緣區域不是純綠色填充,請關閉抗鋸齒功能!!