backend

app.py

@@ -7,6 +7,7 @@ import base64
 import requests
 import time
 from typing import List, Tuple
+from gradio_client.utils import handle_file
 
 # Backend Space URL - replace with your actual backend space URL
 BACKEND_SPACE_URL = "Yuxihenry/SpatialTrackerV2_Backend"  # Replace with actual backend space URL
@@ -218,7 +219,7 @@ def handle_video_upload(video):
                 # Call the unified API with upload_video function type
                 result = backend_client.predict(
                     "upload_video",  # function_type
-                    video,           # video file
+                    handle_file(video),           # video file
                     "",              # original_image_state (not used for upload)
                     [],              # selected_points (not used for upload)
                     "positive_point", # point_type (not used for upload)
@@ -864,7 +865,7 @@ with gr.Blocks(
     gr.Markdown("""
     # 🎯 SpatialTracker V2 - Frontend Interface
     
-    Welcome to SpatialTracker V2! This interface allows you to track objects in videos using advanced computer vision techniques.
+    Welcome to SpatialTracker V2! This interface allows you to track any pixels in 3D using our model.
     
     **Instructions:**
     1. Upload a video file or select from examples below
@@ -958,8 +959,8 @@ with gr.Blocks(
                     ["examples/pillow.mp4"],
                     ["examples/hockey.mp4"],
                     ["examples/drifting.mp4"],
-                    ["examples/ball.mp4"],
                     ["examples/ken_block_0.mp4"],
+                    ["examples/ball.mp4"],
                     ["examples/ego_kc1.mp4"],
                     ["examples/vertical_place.mp4"],
                     ["examples/ego_teaser.mp4"],
@@ -1008,13 +1009,37 @@ with gr.Blocks(
                     interactive=False,
                     height=300
                 )
-                
-            # 3D Visualization
+    
+    # 3D Visualization - Make it larger and more prominent
+    with gr.Row():
+        with gr.Column():
             with gr.Group():
-                gr.Markdown("### 🌐 3D Visualization")
+                gr.Markdown("### 🌐 3D Trajectory Visualization")
+                gr.Markdown("Interactive 3D visualization of 3D point tracking and camera motion:")
                 viz_html = gr.HTML(
                     label="3D Trajectory Visualization",
-                    value="<p>Upload a video and select points to see 3D visualization here.</p>"
+                    value="""
+                    <div style='border: 3px solid #667eea; border-radius: 15px; padding: 40px; 
+                                background: linear-gradient(135deg, #f8f9ff 0%, #e6f3ff 100%); 
+                                text-align: center; min-height: 600px; display: flex; 
+                                flex-direction: column; justify-content: center; align-items: center;
+                                box-shadow: 0 8px 32px rgba(102, 126, 234, 0.2);'>
+                        <div style='font-size: 48px; margin-bottom: 20px;'>🌐</div>
+                        <h2 style='color: #667eea; margin-bottom: 15px; font-size: 28px; font-weight: 600;'>
+                            3D Trajectory Visualization
+                        </h2>
+                        <p style='color: #666; font-size: 16px; line-height: 1.6; max-width: 500px; margin-bottom: 25px;'>
+                            Perceive the world with Pixel-wise 3D Motions!
+                        </p>
+                        <div style='background: rgba(102, 126, 234, 0.1); border-radius: 25px; 
+                                    padding: 12px 24px; border: 2px solid rgba(102, 126, 234, 0.2);'>
+                            <span style='color: #667eea; font-weight: 600; font-size: 14px;'>
+                                ⚡ Powered by SpatialTracker V2
+                            </span>
+                        </div>
+                    </div>
+                    """,
+                    elem_id="viz_container"
                 )
     
     # Advanced settings section - changed to open=True
@@ -1084,6 +1109,45 @@ with gr.Blocks(
         outputs=[viz_html, tracking_result_video]
     )
 
+    # Acknowledgment section for TAPIR3D - moved to the end
+    gr.HTML("""
+    <div style='background: linear-gradient(135deg, #fff8e1 0%, #fffbf0 100%); 
+                border-radius: 8px; 
+                padding: 12px; 
+                margin: 15px 0; 
+                box-shadow: 0 1px 4px rgba(255, 193, 7, 0.1);
+                border: 1px solid rgba(255, 193, 7, 0.2);'>
+        <div style='text-align: center; color: #5d4037;'>
+            <h5 style='margin: 0 0 6px 0; font-size: 14px; color: #5d4037;'>
+                🙏 Acknowledgments
+            </h5>
+            <p style='margin: 0; font-size: 12px; opacity: 0.9; color: #5d4037; line-height: 1.3;'>
+                Our 3D visualizer is adapted from <strong>TAPIP3D</strong>. We thank the authors for their excellent work!
+            </p>
+            <div style='margin-top: 6px;'>
+                <a href="https://github.com/zbw001/TAPIP3D" 
+                   target="_blank" 
+                   style='display: inline-flex; 
+                          align-items: center; 
+                          gap: 3px; 
+                          background: rgba(255, 193, 7, 0.15); 
+                          color: #5d4037; 
+                          padding: 3px 10px; 
+                          border-radius: 12px; 
+                          text-decoration: none; 
+                          font-weight: 500; 
+                          font-size: 11px;
+                          border: 1px solid rgba(255, 193, 7, 0.3);
+                          transition: all 0.3s ease;'
+                   onmouseover="this.style.background='rgba(255, 193, 7, 0.2)'"
+                   onmouseout="this.style.background='rgba(255, 193, 7, 0.15)'">
+                    📚 TAPIP3D Repository
+                </a>
+            </div>
+        </div>
+    </div>
+    """)
+
 # Launch the interface
 if __name__ == "__main__":
     print("🌟 Launching SpatialTracker V2 Frontend...")