HEIC support

app.py

@@ -17,6 +17,10 @@ import gradio as gr
 import numpy as np
 import spaces
 import torch
+from pillow_heif import register_heif_opener
+from PIL import Image
+
+register_heif_opener()
 
 sys.path.append("mapanything/")
 
@@ -117,8 +121,8 @@ def run_model(
     print("Running inference...")
     # apply_mask: Whether to apply the non-ambiguous mask to the output. Defaults to True.
     # mask_edges: Whether to compute an edge mask based on normals and depth and apply it to the output. Defaults to True.
-    # Use checkbox values
-    outputs = model.infer(views, apply_mask=apply_mask, mask_edges=mask_edges)
+    # Use checkbox values - mask_edges is set to True by default since there's no UI control for it
+    outputs = model.infer(views, apply_mask=apply_mask, mask_edges=True)
 
     # Convert predictions to format expected by visualization
     predictions = {}
@@ -389,9 +393,36 @@ def handle_uploads(input_video, input_images, s_time_interval=1.0):
                 file_path = file_data["name"]
             else:
                 file_path = file_data
-            dst_path = os.path.join(target_dir_images, os.path.basename(file_path))
-            shutil.copy(file_path, dst_path)
-            image_paths.append(dst_path)
+            
+            # Check if the file is a HEIC image
+            file_ext = os.path.splitext(file_path)[1].lower()
+            if file_ext in ['.heic', '.heif']:
+                # Convert HEIC to JPEG for better gallery compatibility
+                try:
+                    with Image.open(file_path) as img:
+                        # Convert to RGB if necessary (HEIC can have different color modes)
+                        if img.mode not in ('RGB', 'L'):
+                            img = img.convert('RGB')
+                        
+                        # Create JPEG filename
+                        base_name = os.path.splitext(os.path.basename(file_path))[0]
+                        dst_path = os.path.join(target_dir_images, f"{base_name}.jpg")
+                        
+                        # Save as JPEG with high quality
+                        img.save(dst_path, 'JPEG', quality=95)
+                        image_paths.append(dst_path)
+                        print(f"Converted HEIC to JPEG: {os.path.basename(file_path)} -> {os.path.basename(dst_path)}")
+                except Exception as e:
+                    print(f"Error converting HEIC file {file_path}: {e}")
+                    # Fall back to copying as is
+                    dst_path = os.path.join(target_dir_images, os.path.basename(file_path))
+                    shutil.copy(file_path, dst_path)
+                    image_paths.append(dst_path)
+            else:
+                # Regular image files - copy as is
+                dst_path = os.path.join(target_dir_images, os.path.basename(file_path))
+                shutil.copy(file_path, dst_path)
+                image_paths.append(dst_path)
 
     # --- Handle video ---
     if input_video is not None:
@@ -460,7 +491,6 @@ def gradio_demo(
     filter_black_bg=False,
     filter_white_bg=False,
     apply_mask=True,
-    mask_edges=True,
     show_mesh=True,
 ):
     """
@@ -485,7 +515,7 @@ def gradio_demo(
 
     print("Running MapAnything model...")
     with torch.no_grad():
-        predictions, processed_data = run_model(target_dir, apply_mask, mask_edges)
+        predictions, processed_data = run_model(target_dir, apply_mask)
 
     # Save predictions
     prediction_save_path = os.path.join(target_dir, "predictions.npz")
@@ -1080,7 +1110,9 @@ with gr.Blocks(theme=theme, css=GRADIO_CSS) as demo:
 
         with gr.Column(scale=4):
             with gr.Column():
-                gr.Markdown("**Metric 3D Reconstruction (Point Cloud and Camera Poses)**")
+                gr.Markdown(
+                    "**Metric 3D Reconstruction (Point Cloud and Camera Poses)**"
+                )
                 log_output = gr.Markdown(
                     "Please upload a video or images, then click Reconstruct.",
                     elem_classes=["custom-log"],
@@ -1192,7 +1224,8 @@ with gr.Blocks(theme=theme, css=GRADIO_CSS) as demo:
                     )
                     gr.Markdown("### Reconstruction Options: (updated on next run)")
                     apply_mask_checkbox = gr.Checkbox(
-                        label="Apply mask for predicted ambiguous depth classes & edges", value=True
+                        label="Apply mask for predicted ambiguous depth classes & edges",
+                        value=True,
                     )
     # ---------------------- Example Scenes Section ----------------------
     gr.Markdown("## Example Scenes (lists all scenes in the examples folder)")

mapanything/utils/hf_utils/css_and_html.py

@@ -148,7 +148,7 @@ def get_description_html():
         </details>
         </li>
     </ol>
-    <p><strong style="color: #555555;">Please note:</strong> <span style="color: #555555;">Our model itself usually only needs less than 1 second to reconstruct a scene. However, visualizing 3D points may take tens of seconds due to third-party rendering, which is independent of MapAnything's processing time. Please be patient or, for faster visualization, use a local machine to run our demo from our <a href="https://github.com/facebookresearch/map-anything">GitHub repository</a>. </span></p>
+    <p><strong style="color: #555555;">Please note:</strong> <span style="color: #555555;">Depending on the amount of images, our model usually only needs about 1 second to reconstruct a scene. However, downloading model weights and visualizing 3D points may take tens of seconds. Please be patient or, for faster visualization, use a local machine to run our demo from our <a href="https://github.com/facebookresearch/map-anything">GitHub repository</a>. </span></p>
     </div>
     """