+
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
+
+[**Lihe Yang**](https://liheyoung.github.io/)
1 · [**Bingyi Kang**](https://scholar.google.com/citations?user=NmHgX-wAAAAJ)
2† · [**Zilong Huang**](http://speedinghzl.github.io/)
2 · [**Xiaogang Xu**](https://xiaogang00.github.io/)
3,4 · [**Jiashi Feng**](https://sites.google.com/site/jshfeng/)
2 · [**Hengshuang Zhao**](https://hszhao.github.io/)
1*
+
+
1HKU
2TikTok
3CUHK
4ZJU
+
+†project lead *corresponding author
+
+**CVPR 2024**
+
+
+
+
+
+
+
+### [Cyber rabbit monitoring screens](https://twitter.com/hayas1357/status/1749298607260316139)
+
+
+
+### [Astronaut cat](https://twitter.com/nanase_ja/status/1749653152406884392)
+
+
+
+### [Animation images](https://twitter.com/PlayShingo/status/1750368475867128200)
+
+
+
+### [DALL·E bear](https://twitter.com/letalvoj/status/1749341999646347741)
+
+
+
+### [Cat](https://twitter.com/sajilobroker/status/1749364184419016846)
+
+
+
+### [Surprised bald man](https://twitter.com/mayfer/status/1749712454408679780)
+
+
+
+### [Minecraft](https://twitter.com/BarlowTwin/status/1749353070008693224)
+
+
+
+### [Robotic knight amidst lightning](https://twitter.com/IterIntellectus/status/1749432836158021738)
+
+
+
+### [Football game](https://twitter.com/AB9Mamun/status/1751202608545456235)
+
+
+
+### [Classical raft painting](https://twitter.com/acidbjazz/status/1749491155698331774)
+
+
+
+### [Diner scene](https://twitter.com/R0b0tSp1der/status/1749301061964435846)
+
+
+
+### [Elon Musk](https://twitter.com/ai_for_success/status/1749304903418482954)
+
+
+
+### [Painted tunnel](https://twitter.com/NodiMend/status/1750800040304492814)
+
+
+
+### [Iron man](https://twitter.com/ai_for_success/status/1749304906664808751)
+
+
+
+### [Skull](https://twitter.com/ai_for_success/status/1749304909730906381)
+
+
+
+### [Chibi cat-eared character](https://twitter.com/nanase_ja/status/1749484958522204605)
+
+
+
+### [Exuberant gamer celebration](https://twitter.com/hmaon/status/1749372352016625748)
+
+
+
+### [Ocean](https://twitter.com/jarrahorphin/status/1749878678111309870)
+
+
+
+### [Aerial images](https://twitter.com/lTlanual/status/1749641678124892384)
+
+
+
+### [Grilled chicken skewers](https://twitter.com/promptlord/status/1752323556409856157)
+
+
+
+### [Artistic images](https://twitter.com/ZainHasan6/status/1753553755998416933)
+
+
+
+### [Iconic distracted man](https://twitter.com/ZainHasan6/status/1749308193237303620)
+
+
+
+### [Eye-stalked](https://twitter.com/RJdoesVR/status/1749494967800590780)
+
+
+
+### [Tearful green frog](https://twitter.com/qsdnl/status/1749298425064313080)
+
+
+
+
+## Video
+
+For more online showcases, please refer to https://twitter.com/WilliamLamkin/status/1755623301907460582.
+
+The videos below may be slow to load. Please wait a moment.
+
+### [Racing game](https://twitter.com/i/status/1750683014152040853)
+
+
+
+### [Building](https://twitter.com/WayneINR/status/1750945037863551247)
+
+
+
+### [nuScenes](https://github.com/scepter914/DepthAnything-ROS)
+
+
+
+### [Indoor moving](https://twitter.com/PINTO03091/status/1750162506453041437)
+
+
+
+
+## 3D
+
+The videos below may be slow to load. Please wait a moment.
+
+### [3D visualization](https://twitter.com/victormustar/status/1753008143469093212)
+
+
+
+### [2D videos to 3D videos](https://twitter.com/stspanho/status/1751709292913143895)
+
+
+
+### Reconstruction
+
+- [case1](https://twitter.com/Artoid_XYZ/status/1751542601772421378)
+
+
+
+- [case2](https://twitter.com/DennisLoevlie/status/1753846358463709489)
+
+
+
diff --git a/computervision/depths/gallery.md:Zone.Identifier b/computervision/depths/gallery.md:Zone.Identifier
new file mode 100644
index 0000000..e69de29
diff --git a/computervision/depths/newapp.py b/computervision/depths/newapp.py
new file mode 100644
index 0000000..3d4e168
--- /dev/null
+++ b/computervision/depths/newapp.py
@@ -0,0 +1,70 @@
+from depth_anything.dpt import DepthAnything
+from depth_anything.util.transform import Resize, NormalizeImage, PrepareForNet
+import numpy as np
+import cv2
+import torch
+from torchvision.transforms import Compose
+
+encoder = 'vits' # can also be 'vitb' or 'vitl'
+depth_anything = DepthAnything.from_pretrained('LiheYoung/depth_anything_{:}14'.format(encoder)).eval()
+
+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(),
+])
+
+image = cv2.cvtColor(cv2.imread('DSC01677.jpg'), cv2.COLOR_BGR2RGB) / 255.0
+image = transform({'image': image})['image']
+image = torch.from_numpy(image).unsqueeze(0)
+
+# depth shape: 1xHxW
+depth = depth_anything(image)
+# Run the depth estimation model on the current frame
+# The pipeline returns a dict with key "depth"
+print(depth)
+
+
+
+
+def save_tensor_as_image(tensor, filename):
+ # Konverter til NumPy, frakoble fra beregningsgrafen og flytt til CPU
+ tensor = tensor.detach().cpu().numpy()
+
+ # Fjern unødvendige dimensjoner
+ tensor = np.squeeze(tensor)
+
+ # Normaliser til 0-255 og konverter til uint8
+ tensor_norm = (tensor - np.min(tensor)) / (np.max(tensor) - np.min(tensor))
+ tensor_uint8 = (tensor_norm * 255).astype(np.uint8)
+
+ # Lagre bildet
+ cv2.imwrite(filename, tensor_uint8)
+
+# Bruk funksjonen til å lagre bildene
+save_tensor_as_image(depth, "dybdeimage3.png")
+save_tensor_as_image(depth, "depth_map.jpg")
+
+
+
+"""
+tensor = depth.cpu().numpy() # make sure tensor is on cpu
+cv2.imwrite(tensor, "Dybde.png")
+
+depth_map = depth
+# Ensure depth_map is a numpy array (if not already)
+# save depth map
+cv2.imwrite("depth_map.jpg", depth_map)
+
+"""
+
+
+
diff --git a/computervision/depths/newapp.py:Zone.Identifier b/computervision/depths/newapp.py:Zone.Identifier
new file mode 100644
index 0000000..e69de29
diff --git a/computervision/depths/requirements.txt b/computervision/depths/requirements.txt
new file mode 100644
index 0000000..4044895
--- /dev/null
+++ b/computervision/depths/requirements.txt
@@ -0,0 +1,6 @@
+gradio_imageslider
+gradio==4.14.0
+torch
+torchvision
+opencv-python
+huggingface_hub
\ No newline at end of file
diff --git a/computervision/depths/requirements.txt:Zone.Identifier b/computervision/depths/requirements.txt:Zone.Identifier
new file mode 100644
index 0000000..e69de29
diff --git a/computervision/depths/run.py b/computervision/depths/run.py
new file mode 100644
index 0000000..06c7716
--- /dev/null
+++ b/computervision/depths/run.py
@@ -0,0 +1,113 @@
+import argparse
+import cv2
+import numpy as np
+import os
+import torch
+import torch.nn.functional as F
+from torchvision.transforms import Compose
+from tqdm import tqdm
+
+from depth_anything.dpt import DepthAnything
+from depth_anything.util.transform import Resize, NormalizeImage, PrepareForNet
+
+
+if __name__ == '__main__':
+ parser = argparse.ArgumentParser()
+ parser.add_argument('--img-path', type=str)
+ parser.add_argument('--outdir', type=str, default='./vis_depth')
+ parser.add_argument('--encoder', type=str, default='vitl', choices=['vits', 'vitb', 'vitl'])
+
+ parser.add_argument('--pred-only', dest='pred_only', action='store_true', help='only display the prediction')
+ parser.add_argument('--grayscale', dest='grayscale', action='store_true', help='do not apply colorful palette')
+
+ args = parser.parse_args()
+
+ margin_width = 50
+ caption_height = 60
+
+ font = cv2.FONT_HERSHEY_SIMPLEX
+ font_scale = 1
+ font_thickness = 2
+
+ 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.img_path):
+ if args.img_path.endswith('txt'):
+ with open(args.img_path, 'r') as f:
+ filenames = f.read().splitlines()
+ else:
+ filenames = [args.img_path]
+ else:
+ filenames = os.listdir(args.img_path)
+ filenames = [os.path.join(args.img_path, filename) for filename in filenames if not filename.startswith('.')]
+ filenames.sort()
+
+ os.makedirs(args.outdir, exist_ok=True)
+
+ for filename in tqdm(filenames):
+ raw_image = cv2.imread(filename)
+ image = cv2.cvtColor(raw_image, cv2.COLOR_BGR2RGB) / 255.0
+
+ h, w = image.shape[:2]
+
+ image = transform({'image': image})['image']
+ image = torch.from_numpy(image).unsqueeze(0).to(DEVICE)
+
+ with torch.no_grad():
+ depth = depth_anything(image)
+
+ depth = F.interpolate(depth[None], (h, w), mode='bilinear', align_corners=False)[0, 0]
+ depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0
+
+ depth = depth.cpu().numpy().astype(np.uint8)
+
+ if args.grayscale:
+ depth = np.repeat(depth[..., np.newaxis], 3, axis=-1)
+ else:
+ depth = cv2.applyColorMap(depth, cv2.COLORMAP_INFERNO)
+
+ filename = os.path.basename(filename)
+
+ if args.pred_only:
+ cv2.imwrite(os.path.join(args.outdir, filename[:filename.rfind('.')] + '_depth.png'), depth)
+ else:
+ split_region = np.ones((raw_image.shape[0], margin_width, 3), dtype=np.uint8) * 255
+ combined_results = cv2.hconcat([raw_image, split_region, depth])
+
+ caption_space = np.ones((caption_height, combined_results.shape[1], 3), dtype=np.uint8) * 255
+ captions = ['Raw image', 'Depth Anything']
+ segment_width = w + margin_width
+
+ for i, caption in enumerate(captions):
+ # Calculate text size
+ text_size = cv2.getTextSize(caption, font, font_scale, font_thickness)[0]
+
+ # Calculate x-coordinate to center the text
+ text_x = int((segment_width * i) + (w - text_size[0]) / 2)
+
+ # Add text caption
+ cv2.putText(caption_space, caption, (text_x, 40), font, font_scale, (0, 0, 0), font_thickness)
+
+ final_result = cv2.vconcat([caption_space, combined_results])
+
+ cv2.imwrite(os.path.join(args.outdir, filename[:filename.rfind('.')] + '_img_depth.png'), final_result)
+
\ No newline at end of file
diff --git a/computervision/depths/run.py:Zone.Identifier b/computervision/depths/run.py:Zone.Identifier
new file mode 100644
index 0000000..e69de29
diff --git a/computervision/depths/run_video.py b/computervision/depths/run_video.py
new file mode 100644
index 0000000..16edb66
--- /dev/null
+++ b/computervision/depths/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()
diff --git a/computervision/depths/run_video.py:Zone.Identifier b/computervision/depths/run_video.py:Zone.Identifier
new file mode 100644
index 0000000..e69de29
diff --git a/computervision/objectdetection/yolov8.py b/computervision/objectdetection/yolov8.py
new file mode 100644
index 0000000..bb68fa8
--- /dev/null
+++ b/computervision/objectdetection/yolov8.py
@@ -0,0 +1,64 @@
+from ultralytics import YOLO
+import cv2
+import math
+# start webcam
+cap = cv2.VideoCapture("WIN_20250225_22_33_58_Pro.mp4")
+cap.set(3, 640)
+cap.set(4, 480)
+
+# model
+model = YOLO("yolo-Weights/yolov8n.pt")
+
+# object classes
+classNames = ["person", "bicycle", "car", "motorbike", "aeroplane", "bus", "train", "truck", "boat",
+ "traffic light", "fire hydrant", "stop sign", "parking meter", "bench", "bird", "cat",
+ "dog", "horse", "sheep", "cow", "elephant", "bear", "zebra", "giraffe", "backpack", "umbrella",
+ "handbag", "tie", "suitcase", "frisbee", "skis", "snowboard", "sports ball", "kite", "baseball bat",
+ "baseball glove", "skateboard", "surfboard", "tennis racket", "bottle", "wine glass", "cup",
+ "fork", "knife", "spoon", "bowl", "banana", "apple", "sandwich", "orange", "broccoli",
+ "carrot", "hot dog", "pizza", "donut", "cake", "chair", "sofa", "pottedplant", "bed",
+ "diningtable", "toilet", "tvmonitor", "laptop", "mouse", "remote", "keyboard", "cell phone",
+ "microwave", "oven", "toaster", "sink", "refrigerator", "book", "clock", "vase", "scissors",
+ "teddy bear", "hair drier", "toothbrush"
+ ]
+
+
+while True:
+ success, img = cap.read()
+ results = model(img, stream=True)
+
+ # coordinates
+ for r in results:
+ boxes = r.boxes
+
+ for box in boxes:
+ # bounding box
+ x1, y1, x2, y2 = box.xyxy[0]
+ x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2) # convert to int values
+
+ # put box in cam
+ cv2.rectangle(img, (x1, y1), (x2, y2), (255, 0, 255), 3)
+
+ # confidence
+ confidence = math.ceil((box.conf[0]*100))/100
+ print("Confidence --->",confidence)
+
+ # class name
+ cls = int(box.cls[0])
+ print("Class name -->", classNames[cls])
+
+ # object details
+ org = [x1, y1]
+ font = cv2.FONT_HERSHEY_SIMPLEX
+ fontScale = 1
+ color = (255, 0, 0)
+ thickness = 2
+
+ cv2.putText(img, classNames[cls], org, font, fontScale, color, thickness)
+
+ cv2.imshow('Webcam', img)
+ if cv2.waitKey(1) == ord('q'):
+ break
+
+cap.release()
+cv2.destroyAllWindows()
\ No newline at end of file
diff --git a/computervision/objectdetection/yolov8.py:Zone.Identifier b/computervision/objectdetection/yolov8.py:Zone.Identifier
new file mode 100644
index 0000000..e69de29