Duplicate from Sentdex/LookingGlassRGBD

Co-authored-by: Harrison Kinsley <Sentdex@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: LookinGlassRGBD
+emoji: 👁
+colorFrom: yellow
+colorTo: gray
+sdk: gradio
+sdk_version: 3.11.0
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: Sentdex/LookingGlassRGBD
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,68 @@
+import cv2
+import torch
+import gradio as gr
+import numpy as np
+from PIL import Image
+import time
+
+midas = torch.hub.load("intel-isl/MiDaS", "MiDaS")
+
+use_large_model = True
+
+if use_large_model:
+    midas = torch.hub.load("intel-isl/MiDaS", "MiDaS")
+else:
+    midas = torch.hub.load("intel-isl/MiDaS", "MiDaS_small")
+
+device = "cpu"
+midas.to(device)
+
+midas_transforms = torch.hub.load("intel-isl/MiDaS", "transforms")
+
+if use_large_model:
+    transform = midas_transforms.default_transform
+else:
+    transform = midas_transforms.small_transform
+
+
+def depth(img):
+  original_image = img
+  cv_image = np.array(img) 
+  img = cv2.cvtColor(cv_image, cv2.COLOR_BGR2RGB)
+
+  input_batch = transform(img).to(device)
+  with torch.no_grad():
+    prediction = midas(input_batch)
+
+    prediction = torch.nn.functional.interpolate(
+        prediction.unsqueeze(1),
+        size=img.shape[:2],
+        mode="bicubic",
+        align_corners=False,
+    ).squeeze()
+    
+  output = prediction.cpu().numpy()
+  formatted = (output * 255 / np.max(output)).astype('uint8')
+  img = Image.fromarray(formatted)
+
+  # create new image with with original_image and img side by side
+  new_im = Image.new('RGB', (original_image.width * 2, original_image.height))
+  new_im.paste(original_image, (0,0))
+  new_im.paste(img, (original_image.width,0))
+
+  # save the image to a file: (removed for hosting on HF)
+  #new_im.save(f'RGBDs/{int(time.time())}_RGBD.png')
+
+
+  return new_im
+    
+
+inputs =  gr.inputs.Image(type='pil', label="Original Image")
+outputs = gr.outputs.Image(type="pil",label="Output Image")
+
+title = "RGB to RGBD for Looking Glass (using MiDaS)"
+description = "Takes an RGB image and creates the depth + combines to the RGB image. Depth is predicted by MiDaS. This is a demo of the Looking Glass. For more information, visit https://lookingglassfactory.com"
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/1907.01341v3'>Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer</a> | <a href='https://github.com/intel-isl/MiDaS'>Github Repo</a></p>"
+
+
+gr.Interface(depth, inputs, outputs, title=title, description=description, article=article).launch()

requirements.txt

@@ -0,0 +1,7 @@
+opencv-python
+timm
+torch~=1.8
+torchvision
+opencv-python-headless
+numpy
+Pillow