Simple helper to visualize masks (#3)

- Simple helper to visualize masks (33ef473408dc097b28115dae73221fd417c8c0ac)
- Remove comment (aea8749833b53bd864a29d3908f31ec9115f1dde)


Co-authored-by: Pedro Cuenca <pcuenq@users.noreply.huggingface.co>

README.md

@@ -124,6 +124,38 @@ SAM3 performs Promptable Concept Segmentation (PCS) on images, taking text and/o
 >>> # - scores: Confidence scores
 ```
 
+You can display masks using a simple helper like the following:
+
+```python
+import numpy as np
+import matplotlib
+
+def overlay_masks(image, masks):
+    image = image.convert("RGBA")
+    masks = 255 * masks.cpu().numpy().astype(np.uint8)
+    
+    n_masks = masks.shape[0]
+    cmap = matplotlib.colormaps.get_cmap("rainbow").resampled(n_masks)
+    colors = [
+        tuple(int(c * 255) for c in cmap(i)[:3])
+        for i in range(n_masks)
+    ]
+
+    for mask, color in zip(masks, colors):
+        mask = Image.fromarray(mask)
+        overlay = Image.new("RGBA", image.size, color + (0,))
+        alpha = mask.point(lambda v: int(v * 0.5))
+        overlay.putalpha(alpha)
+        image = Image.alpha_composite(image, overlay)
+    return image
+```
+
+Then you can save the resulting composite image or display it in a notebook:
+
+```python
+>>> overlay_masks(image, results["masks"])
+```
+
 #### Single Bounding Box Prompt
 
 Segment objects using a bounding box:
@@ -187,6 +219,7 @@ Use multiple boxes with positive and negative labels to refine the concept:
 ...     mask_threshold=0.5,
 ...     target_sizes=inputs.get("original_sizes").tolist()
 ... )[0]
+>>> overlay_masks(kitchen_image, results["masks"])
 ```
 
 #### Combined Prompts (Text + Negative Box)