File size: 1,956 Bytes
831c6b2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
import gradio as gr
from transformers import DPTFeatureExtractor, DPTForDepthEstimation
import torch
import numpy as np
from PIL import Image
from pathlib import Path
from depth_viewer import depthviewer2html

feature_extractor = DPTFeatureExtractor.from_pretrained("Intel/dpt-large")
model = DPTForDepthEstimation.from_pretrained("Intel/dpt-large")

def process_image(image_path):
    image_path = Path(image_path)
    image = Image.open(image_path)

    # prepare image for the model
    encoding = feature_extractor(image, return_tensors="pt")

    # forward pass
    with torch.no_grad():
        outputs = model(**encoding)
        predicted_depth = outputs.predicted_depth

    # interpolate to original size
    prediction = torch.nn.functional.interpolate(
        predicted_depth.unsqueeze(1),
        size=image.size[::-1],
        mode="bicubic",
        align_corners=False,
    ).squeeze()
    output = prediction.cpu().numpy()
    depth = (output * 255 / np.max(output)).astype('uint8')

    h = depthviewer2html(image,depth)
    return [h]

title = "3d Visualization of Depth Maps Generated using MiDaS"
description = "Improved 3D interactive depth viewer using Three.js embedded in a Gradio app. For more details see the <a href='https://colab.research.google.com/drive/1l2l8U7Vhq9RnvV2tHyfhrXKNuHfmb4IP?usp=sharing'>Colab Notebook.</a>"
examples = [["examples/owl1.jpg"],['examples/marsattacks.jpg'],['examples/kitten.jpg']]

iface = gr.Interface(fn=process_image,
                     inputs=[gr.Image(type="filepath",label="Input Image")],
                     outputs=[gr.HTML(label='Depth Viewer',elem_id='depth-viewer')],
                     title=title,
                     description=description,
                     examples=examples,
                     allow_flagging="never",
                     cache_examples=False,
                     css='#depth-viewer: {height:300px;}')

iface.launch(debug=True, enable_queue=False)