Update README.md

README.md

@@ -9,34 +9,11 @@ pinned: false
 
 # LiveCompose
 
-LiveCompose is a team project focused on intelligent image cropping for mobile deployment.
+LiveCompose explores intelligent image composition, outpainting, and automatic cropping for mobile deployment.
 
-## Projects
+This organization hosts:
+- **Spaces**: the AdaCrop image cropping demo.
+- **Models**: original AdaCrop PyTorch checkpoints, distilled MobileNetV3 student models, and Core ML exports for iOS.
+- **Datasets**: outpainted image data with crop bounding boxes for training.
 
-### Spaces
-
-- **Adacrop Demo**  
-  Interactive demo for Adacrop, an automatic image cropping system. The demo shows how a trained cropping policy predicts an initial crop box and refines it through sequential actions.
-
-## Models
-
-- **Adacrop**  
-  Original PyTorch checkpoints for the AdaCrop model, including the ResNet-50-based Actor-Critic policy and BBox head.
-
-- **Adacrop-MNV3-Distilled**  
-  A distilled MobileNetV3 student version of AdaCrop, designed to reduce model size and make mobile deployment more practical.
-
-- **Adacrop-CoreML.mlpackage**  
-  Core ML exports of Adacrop components for iOS deployment, including BBox prediction and policy action models.
-
-## Datasets
-
-- **LiveCompose-outpainted-17K**  
-  Outpainted image dataset with original crop bounding boxes, used for crop prediction and policy distillation experiments.
-
-## About AdaCrop
-
-AdaCrop formulates image cropping as a two-stage process:
-
-1. A BBox head predicts an initial crop region.
-2. An Actor policy refines the crop through actions such as moving, zooming, and stopping. 
+AdaCrop uses a two-stage cropping pipeline: a BBox head predicts an initial crop region, then an Actor policy refines the crop through sequential actions such as move, zoom, and stop.