Upload app.py

app.py

@@ -381,7 +381,7 @@ def add_mask(mask, mask_list):
 def vis_mask(image, mask_list):
     updated_image = image.copy()
     # combine all the mask:
-    combined_mask = np.zeros_like(updated_image)
+    combined_mask = np.zeros_like(mask_list[0])
     for mask in mask_list:
         combined_mask = cv2.bitwise_or(combined_mask, mask)
     # overlay the mask on the image
@@ -390,23 +390,8 @@ def vis_mask(image, mask_list):
 
 
 with gr.Blocks(delete_cache=(600, 600)) as demo:
-    # gr.Markdown("""
-    # ## 3D Amodal Reconstruction with [Amodal3R](https://sm0kywu.github.io/Amodal3R/)
-    # * Upload an image and click "Generate" to create a 3D asset.
-    # * Target object selection. Multiple point prompts are supported until you get the ideal visible area.
-    # * Occluders selection, this can be done by squential point prompts. You can choose "all occ", then all the other areas except the target object will be treated as occluders.
-    # * Different random seeds can be tried in "Generation Settings", if you think the results are not ideal. 
-    # * If the reconstruction 3D asset is satisfactory, you can extract the GLB file and download it.
-    # """)
     gr.Markdown("""
-    ## 3D Amodal Reconstruction with [Amodal3R](https://sm0kywu.github.io/Amodal3R/)
-    * Step 1 - Generate Visibility Mask and Occlusion Mask.
-    * Please wait for a few seconds after uploading the image. The 2D segmenter is getting ready.
-    * Add the point prompts to indicate the target object and occluders separately.
-    * "Render Point", see the position of the point to be added.
-    * "Add Point", the point will be added to the list.
-    * "Generate mask", see the segmented area corresponding to current point list.
-    * "Add mask", current mask will be added for 3D amodal completion.          
+    ## 3D Amodal Reconstruction with [Amodal3R](https://sm0kywu.github.io/Amodal3R/)          
     """)
 
      # 定义各状态变量
@@ -421,6 +406,14 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
 
 
     with gr.Row():
+        gr.Markdown("""* Step 1 - Generate Visibility Mask and Occlusion Mask.
+        * Please wait for a few seconds after uploading the image. The 2D segmenter is getting ready.
+        * Add the point prompts to indicate the target object and occluders separately.
+        * "Render Point", see the position of the point to be added.
+        * "Add Point", the point will be added to the list.
+        * "Generate mask", see the segmented area corresponding to current point list.
+        * "Add mask", current mask will be added for 3D amodal completion.
+        """)
         with gr.Column():
             input_image = gr.Image(type="numpy", label='Input Occlusion Image', sources="upload", height=300)
             with gr.Row():
@@ -464,7 +457,17 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
                 render_occ_mask = gr.Button("Render Mask")
                 undo_occ_mask = gr.Button("Undo Last Mask")
             # 
-    
+    with gr.Row():
+        gr.Markdown("""* Step 2 - 3D Amodal Completion.
+        * Please first check the obtained mask, and make sure there is no "GAP" between the visible area (white) and occluded area (gray).
+        * Different random seeds can be tried in "Generation Settings", if you think the results are not ideal.
+        * If the reconstruction 3D asset is satisfactory, you can extract the GLB file and download it.
+        """)
+        with gr.Column():
+            combined_mask = gr.Image(label='Combined Mask', interactive=False, height=300)
+            with gr.Row():
+                check_combine_button = gr.Button("Check Combined Mask")
+
     # ---------------------------
     # 原有交互逻辑（略）
     # ---------------------------
@@ -538,7 +541,7 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
     render_vis_mask.click(
         vis_mask,
         inputs=[original_image, visibility_mask_list],
-        outputs=[input_image]
+        outputs=[visible_mask]
     )
     gen_occ_mask.click(
         segment_and_overlay,
@@ -553,7 +556,7 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
     render_occ_mask.click(
         vis_mask,
         inputs=[original_image, occlusion_mask_list],
-        outputs=[input_image]
+        outputs=[occluded_mask]
     )