Support video depth visualization

2026-01-26 15:29:46 +00:00 · 2024-01-25 18:18:29 +08:00
parent 1939e64d67
commit 1ad37271a1
1 changed files with 94 additions and 0 deletions
--- a/run_video.py
+++ b/run_video.py
@@ -0,0 +1,94 @@
+import argparse
+import cv2
+import numpy as np
+import os
+import torch
+import torch.nn.functional as F
+from torchvision.transforms import Compose
+
+from depth_anything.dpt import DepthAnything
+from depth_anything.util.transform import Resize, NormalizeImage, PrepareForNet
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--video-path', type=str)
+    parser.add_argument('--outdir', type=str, default='./vis_video_depth')
+    parser.add_argument('--encoder', type=str, default='vitl', choices=['vits', 'vitb', 'vitl'])
+    
+    args = parser.parse_args()
+    
+    margin_width = 50
+
+    DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
+    
+    depth_anything = DepthAnything.from_pretrained('LiheYoung/depth_anything_{}14'.format(args.encoder)).to(DEVICE).eval()
+    
+    total_params = sum(param.numel() for param in depth_anything.parameters())
+    print('Total parameters: {:.2f}M'.format(total_params / 1e6))
+    
+    transform = Compose([
+        Resize(
+            width=518,
+            height=518,
+            resize_target=False,
+            keep_aspect_ratio=True,
+            ensure_multiple_of=14,
+            resize_method='lower_bound',
+            image_interpolation_method=cv2.INTER_CUBIC,
+        ),
+        NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+        PrepareForNet(),
+    ])
+
+    if os.path.isfile(args.video_path):
+        if args.video_path.endswith('txt'):
+            with open(args.video_path, 'r') as f:
+                lines = f.read().splitlines()
+        else:
+            filenames = [args.video_path]
+    else:
+        filenames = os.listdir(args.video_path)
+        filenames = [os.path.join(args.video_path, filename) for filename in filenames if not filename.startswith('.')]
+        filenames.sort()
+    
+    os.makedirs(args.outdir, exist_ok=True)
+    
+    for k, filename in enumerate(filenames):
+        print('Progress {:}/{:},'.format(k+1, len(filenames)), 'Processing', filename)
+        
+        raw_video = cv2.VideoCapture(filename)
+        frame_width, frame_height = int(raw_video.get(cv2.CAP_PROP_FRAME_WIDTH)), int(raw_video.get(cv2.CAP_PROP_FRAME_HEIGHT))
+        frame_rate = int(raw_video.get(cv2.CAP_PROP_FPS))
+        output_width = frame_width * 2 + margin_width
+        
+        filename = os.path.basename(filename)
+        output_path = os.path.join(args.outdir, filename[:filename.rfind('.')] + '_video_depth.mp4')
+        out = cv2.VideoWriter(output_path, cv2.VideoWriter_fourcc(*"mp4v"), frame_rate, (output_width, frame_height))
+        
+        while raw_video.isOpened():
+            ret, raw_frame = raw_video.read()
+            if not ret:
+                break
+            
+            frame = cv2.cvtColor(raw_frame, cv2.COLOR_BGR2RGB) / 255.0
+            
+            frame = transform({'image': frame})['image']
+            frame = torch.from_numpy(frame).unsqueeze(0).to(DEVICE)
+            
+            with torch.no_grad():
+                depth = depth_anything(frame)
+
+            depth = F.interpolate(depth[None], (frame_height, frame_width), mode='bilinear', align_corners=False)[0, 0]
+            depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0
+            
+            depth = depth.cpu().numpy().astype(np.uint8)
+            depth_color = cv2.applyColorMap(depth, cv2.COLORMAP_INFERNO)
+            
+            split_region = np.ones((frame_height, margin_width, 3), dtype=np.uint8) * 255
+            combined_frame = cv2.hconcat([raw_frame, split_region, depth_color])
+            
+            out.write(combined_frame)
+        
+        raw_video.release()
+        out.release()