c

app.py

@@ -1,5 +1,7 @@
 import gradio as gr
 import numpy as np
+import cv2
+from PIL import Image
 from PIFuHD.data import EvalWMetaDataset
 from PIFuHD.data.ImageBundle import ImageBundle
 from PIFuHD.options import BaseOptions
@@ -9,9 +11,7 @@ from human_pose_estimator import PoseEstimator
 from estimator import rect
 
 REPO_ID = "cxeep/PIFuHD"
-
 pose_estimator = PoseEstimator("cpu")
-
 checkpoint_path = hf_hub_download(repo_id=REPO_ID, filename="pifuhd.pt")
 
 cmd = [
@@ -23,51 +23,74 @@ cmd = [
     '--start_id', '-1',
     '--end_id', '-1'
 ]
-
 parser = BaseOptions()
 opts = parser.parse(cmd)
 reconstructor = Reconstructor(opts)
 
-
 def make_bundle(image, name):
     image, rects = rect(pose_estimator, image)
     return ImageBundle(img=image, name=name, meta=rects)
 
-
-def predict(img: np.ndarray):
-    bundle = make_bundle(img, "Model3D")
-    dataset = EvalWMetaDataset(opts, [bundle])
-    return reconstructor.evaluate(dataset)
-
+def process_video(video_path):
+    frames = []
+    cap = cv2.VideoCapture(video_path)
+    while cap.isOpened():
+        ret, frame = cap.read()
+        if not ret:
+            break
+        frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+        frames.append(Image.fromarray(frame))
+    cap.release()
+    
+    models = []
+    for frame in frames:
+        bundle = make_bundle(np.array(frame), "Model3D")
+        dataset = EvalWMetaDataset(opts, [bundle])
+        model = reconstructor.evaluate(dataset)
+        models.append(model)
+    
+    # TODO: Combine models into animation
+    output_animation = models[0]  # Placeholder, replace with actual animation
+    
+    return output_animation
+
+def predict(input):
+    if isinstance(input, str):  # video 
+        return process_video(input)
+    else:  # image
+        bundle = make_bundle(input, "Model3D")
+        dataset = EvalWMetaDataset(opts, [bundle])
+        return reconstructor.evaluate(dataset)
 
 footer = r"""
 <center>
-<b>
-3D Human Digitization
-</b>
+<b>Demo for <a href='https://github.com/facebookresearch/pifuhd'>PIFuHD</a></b>
 </center>
 """
 
 with gr.Blocks(title="PIFuHD") as app:
     gr.HTML("<center><h1>3D Human Digitization</h1></center>")
+    gr.HTML("<center><h3>PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization (CVPR 2020)</h3></center>")
+    
     with gr.Row(equal_height=False):
         with gr.Column():
             input_img = gr.Image(type="numpy", label="Input image")
+            input_video = gr.Video(type="filepath", label="Input Video")
             run_btn = gr.Button(variant="primary")
         with gr.Column():
             output_obj = gr.Model3D(label="Output model")
             output_img = gr.Image(type="filepath", label="Output image")
-            gr.ClearButton(components=[input_img, output_img, output_obj], variant="stop")
-
-    run_btn.click(predict, [input_img], [output_img, output_obj])
-
+            gr.ClearButton(components=[input_img, input_video, output_img, output_obj], variant="stop")
+    
+    run_btn.click(predict, [input_img, input_video], [output_img, output_obj])
+    
     with gr.Row():
         blobs = [[f"examples/{x:02d}.png"] for x in range(1, 4)]
         examples = gr.Dataset(components=[input_img], samples=blobs)
         examples.click(lambda x: x[0], [examples], [input_img])
-
+    
     with gr.Row():
         gr.HTML(footer)
 
 app.launch(share=False, debug=True, show_error=True)
-app.queue()
+app.queue()