Update README.md

README.md

@@ -14,12 +14,6 @@ Official repository for RobustSAM: Segment Anything Robustly on Degraded Images
 [Project Page](https://robustsam.github.io/) | [Paper](https://arxiv.org/abs/2406.09627) | [Dataset](https://huggingface.co/robustsam/robustsam/tree/main/dataset)
 
 
-## Updates
-- July 2024: ✨ Training code, data and model checkpoints for different ViT backbones are released!
-- June 2024: ✨ Inference code has been released!
-- Feb 2024: ✨ RobustSAM was accepted into CVPR 2024!
-
-
 ## Introduction
 Segment Anything Model (SAM) has emerged as a transformative approach in image segmentation, acclaimed for its robust zero-shot segmentation capabilities and flexible prompting system. Nonetheless, its performance is challenged by images with degraded quality. Addressing this limitation, we propose the Robust Segment Anything Model (RobustSAM), which enhances SAM's performance on low-quality images while preserving its promptability and zero-shot generalization.
 
@@ -120,11 +114,6 @@ plt.axis("off")
 plt.show()
 ```
 
-<img width="1096" alt="image" src="figures/architecture.jpg">
-
-## Comparison of computational requirements
-<img width="720" alt="image" src='figures/Computational requirements.PNG'>
-
 ## Visual Comparison
 <table>
   <tr>
@@ -147,16 +136,6 @@ plt.show()
 
 <img width="1096" alt="image" src='figures/qualitative_result.PNG'>
 
-## Quantitative Comparison
-### Seen dataset with synthetic degradation
-<img width="720" alt="image" src='figures/seen_dataset_with_synthetic_degradation.PNG'>
-
-### Unseen dataset with synthetic degradation
-<img width="720" alt="image" src='figures/unseen_dataset_with_synthetic_degradation.PNG'>
-
-### Unseen dataset with real degradation
-<img width="600" alt="image" src='figures/unseen_dataset_with_real_degradation.PNG'>
-
 ## Reference
 If you find this work useful, please consider citing us!
 ```python