File size: 2,812 Bytes
029b4b5
679bbb3
029b4b5
679bbb3
 
029b4b5
 
 
 
 
 
 
679bbb3
029b4b5
679bbb3
 
029b4b5
02acfac
029b4b5
 
 
 
 
 
 
 
 
 
 
 
 
679bbb3
029b4b5
 
679bbb3
3295ec4
 
029b4b5
 
679bbb3
3295ec4
02acfac
3295ec4
029b4b5
3295ec4
679bbb3
029b4b5
68aeb60
 
 
 
cc376eb
029b4b5
cc376eb
3295ec4
02acfac
029b4b5
70d73db
b547b0c
029b4b5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cc376eb
029b4b5
 
 
 
 
cc376eb
029b4b5
68aeb60
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
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
from doctest import Example
import gradio as gr
from transformers import DPTImageProcessor, DPTForDepthEstimation
import torch
import numpy as np
from PIL import Image, ImageOps
from pathlib import Path
import glob
from autostereogram.converter import StereogramConverter
from datetime import datetime
import time
import tempfile

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

stereo_converter = StereogramConverter()


def process_image(image_path):
    print("\n\n\n")
    print("Processing image:", image_path)
    last_time = time.time()
    image_raw = Image.open(Path(image_path))

    image = image_raw.resize(
        (1280, int(1280 * image_raw.size[1] / image_raw.size[0])),
        Image.Resampling.LANCZOS,
    )

    # 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_image = (output * 255 / np.max(output)).astype("uint8")
    depth_image_padded = np.array(
        ImageOps.pad(Image.fromarray(depth_image), (1280, 720))
    )

   

    return depth_image_padded


examples_images = [[f] for f in sorted(glob.glob("examples/*.jpg"))]


with gr.Blocks() as blocks:
    gr.Markdown(
        """
## Depth Image to Autostereogram (Magic Eye)
This demo is a variation from the original [DPT Demo](https://huggingface.co/spaces/nielsr/dpt-depth-estimation).
Zero-shot depth estimation from an image, then it uses [pystereogram](https://github.com/yxiao1996/pystereogram)
to generate the autostereogram (Magic Eye)
<base target="_blank">
"""
    )
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(type="filepath", label="Input Image")
            button = gr.Button("Predict")
        with gr.Column():
            predicted_depth = gr.Image(label="Predicted Depth", type="pil")
    with gr.Row():
        autostereogram = gr.Image(label="Autostereogram", type="pil")
    with gr.Row():
        with gr.Column():
            file_download = gr.File(label="Download Image")
    with gr.Row():
        gr.Examples(
            examples=examples_images,
            fn=process_image,
            inputs=[input_image],
            outputs=predicted_depth],
            cache_examples=True,
        )
    button.click(
        fn=process_image,
        inputs=[input_image],
        outputs=predicted_depth],
    )
blocks.launch(debug=True)