fix

app.py

@@ -12,13 +12,15 @@ def snap(image, video):
     gltf_path = create_3d_obj(np.array(image), depth_result)
     #segment_predictor = SegmentPredictor()
     #sam_result = segment_predictor.predict(image)
-    return [gltf_path, video]#[depth_result, gltf_path, gltf_path]
+    return [image, gltf_path]#[depth_result, gltf_path, gltf_path]
 
 
 demo = gr.Interface(
     snap,
-    [gr.Image(source="webcam", tool=None, type="pil"), gr.Video(source="webcam")],
-    ["image", "video"],
+    inputs=[gr.Image(source="webcam", tool=None, type="pil"),
+            gr.Video(source="webcam")],
+    outputs=[gr.Image(label="predicted depth", type="pil"),
+             gr.Model3D(label="3d mesh reconstruction", clear_color=[1.0, 1.0, 1.0, 1.0]), gr.File(label="3d gLTF")]
 )
 
 if __name__ == "__main__":