support denoise strength for realesr-general-x4v3

inference_realesrgan.py

@@ -3,6 +3,7 @@ import cv2
 import glob
 import os
 from basicsr.archs.rrdbnet_arch import RRDBNet
+from basicsr.utils.download_util import load_file_from_url
 
 from realesrgan import RealESRGANer
 from realesrgan.archs.srvgg_arch import SRVGGNetCompact
@@ -19,10 +20,18 @@ def main():
         type=str,
         default='RealESRGAN_x4plus',
         help=('Model names: RealESRGAN_x4plus | RealESRNet_x4plus | RealESRGAN_x4plus_anime_6B | RealESRGAN_x2plus | '
-              'realesr-animevideov3 | realesr-general-x4v3 | realesr-general-wdn-x4v3'))
+              'realesr-animevideov3 | realesr-general-x4v3'))
     parser.add_argument('-o', '--output', type=str, default='results', help='Output folder')
-    parser.add_argument('--model_path', type=str, default=None, help='Model path')
+    parser.add_argument(
+        '-dn',
+        '--denoise_strength',
+        type=float,
+        default=0.5,
+        help=('Denoise strength. 0 for weak denoise (keep noise), 1 for strong denoise ability. '
+              'Only used for the realesr-general-x4v3 model'))
     parser.add_argument('-s', '--outscale', type=float, default=4, help='The final upsampling scale of the image')
+    parser.add_argument(
+        '--model_path', type=str, default=None, help='[Option] Model path. Usually, you do not need to specify it')
     parser.add_argument('--suffix', type=str, default='out', help='Suffix of the restored image')
     parser.add_argument('-t', '--tile', type=int, default=0, help='Tile size, 0 for no tile during testing')
     parser.add_argument('--tile_pad', type=int, default=10, help='Tile padding')
@@ -47,36 +56,58 @@ def main():
 
     # determine models according to model names
     args.model_name = args.model_name.split('.')[0]
-    if args.model_name in ['RealESRGAN_x4plus', 'RealESRNet_x4plus']:  # x4 RRDBNet model
+    if args.model_name == 'RealESRGAN_x4plus':  # x4 RRDBNet model
+        model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4)
+        netscale = 4
+        file_url = 'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth'
+    elif args.model_name == 'RealESRNet_x4plus':  # x4 RRDBNet model
         model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4)
         netscale = 4
-    elif args.model_name in ['RealESRGAN_x4plus_anime_6B']:  # x4 RRDBNet model with 6 blocks
+        file_url = 'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/RealESRNet_x4plus.pth'
+    elif args.model_name == 'RealESRGAN_x4plus_anime_6B':  # x4 RRDBNet model with 6 blocks
         model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=6, num_grow_ch=32, scale=4)
         netscale = 4
-    elif args.model_name in ['RealESRGAN_x2plus']:  # x2 RRDBNet model
+        file_url = 'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth'
+    elif args.model_name == 'RealESRGAN_x2plus':  # x2 RRDBNet model
         model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=2)
         netscale = 2
-    elif args.model_name in ['realesr-animevideov3']:  # x4 VGG-style model (XS size)
+        file_url = 'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth'
+    elif args.model_name == 'realesr-animevideov3':  # x4 VGG-style model (XS size)
         model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=16, upscale=4, act_type='prelu')
         netscale = 4
-    elif args.model_name in ['realesr-general-x4v3', 'realesr-general-wdn-x4v3']:  # x4 VGG-style model (S size)
+        file_url = 'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth'
+    elif args.model_name == 'realesr-general-x4v3':  # x4 VGG-style model (S size)
         model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
         netscale = 4
+        file_url = [
+            'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-wdn-x4v3.pth',
+            'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth'
+        ]
 
     # determine model paths
     if args.model_path is not None:
         model_path = args.model_path
     else:
-        model_path = os.path.join('experiments/pretrained_models', args.model_name + '.pth')
-        if not os.path.isfile(model_path):
-            model_path = os.path.join('realesrgan/weights', args.model_name + '.pth')
+        model_path = os.path.join('realesrgan/weights', args.model_name + '.pth')
         if not os.path.isfile(model_path):
-            raise ValueError(f'Model {args.model_name} does not exist.')
+            ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+            for url in file_url:
+                # model_path will be updated
+                model_path = load_file_from_url(
+                    url=url, model_dir=os.path.join(ROOT_DIR, 'realesrgan/weights'), progress=True, file_name=None)
+
+    # use dni to control the denoise strength
+    dni_weight = None
+    if args.model_name == 'realesr-general-x4v3' and args.denoise_strength != 1:
+        wdn_model_path = model_path.replace('realesr-general-x4v3', 'realesr-general-wdn-x4v3')
+        model_path = [model_path, wdn_model_path]
+        dni_weight = [args.denoise_strength, 1 - args.denoise_strength]
 
     # restorer
     upsampler = RealESRGANer(
         scale=netscale,
         model_path=model_path,
+        dni_weight=dni_weight,
         model=model,
         tile=args.tile,
         tile_pad=args.tile_pad,

realesrgan/utils.py

@@ -29,6 +29,7 @@ class RealESRGANer():
     def __init__(self,
                  scale,
                  model_path,
+                 dni_weight=None,
                  model=None,
                  tile=0,
                  tile_pad=10,
@@ -49,22 +50,44 @@ class RealESRGANer():
                 f'cuda:{gpu_id}' if torch.cuda.is_available() else 'cpu') if device is None else device
         else:
             self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') if device is None else device
-        # if the model_path starts with https, it will first download models to the folder: realesrgan/weights
-        if model_path.startswith('https://'):
-            model_path = load_file_from_url(
-                url=model_path, model_dir=os.path.join(ROOT_DIR, 'realesrgan/weights'), progress=True, file_name=None)
-        loadnet = torch.load(model_path, map_location=torch.device('cpu'))
+
+        if isinstance(model_path, list):
+            # dni
+            assert len(model_path) == len(dni_weight), 'model_path and dni_weight should have the save length.'
+            loadnet = self.dni(model_path[0], model_path[1], dni_weight)
+        else:
+            # if the model_path starts with https, it will first download models to the folder: realesrgan/weights
+            if model_path.startswith('https://'):
+                model_path = load_file_from_url(
+                    url=model_path,
+                    model_dir=os.path.join(ROOT_DIR, 'realesrgan/weights'),
+                    progress=True,
+                    file_name=None)
+            loadnet = torch.load(model_path, map_location=torch.device('cpu'))
+
         # prefer to use params_ema
         if 'params_ema' in loadnet:
             keyname = 'params_ema'
         else:
             keyname = 'params'
         model.load_state_dict(loadnet[keyname], strict=True)
+
         model.eval()
         self.model = model.to(self.device)
         if self.half:
             self.model = self.model.half()
 
+    def dni(self, net_a, net_b, dni_weight, key='params', loc='cpu'):
+        """Deep network interpolation.
+
+        ``Paper: Deep Network Interpolation for Continuous Imagery Effect Transition``
+        """
+        net_a = torch.load(net_a, map_location=torch.device(loc))
+        net_b = torch.load(net_b, map_location=torch.device(loc))
+        for k, v_a in net_a[key].items():
+            net_a[key][k] = dni_weight[0] * v_a + dni_weight[1] * net_b[key][k]
+        return net_a
+
     def pre_process(self, img):
         """Pre-process, such as pre-pad and mod pad, so that the images can be divisible
         """