Segment object in noisy image with SAM by standardize the variation in degraded image with RobustSAM
Segment object in noisy image with SAM by standardize the variation in degraded image with RobustSAM
RobustSAM: Segment Anything Robustly on Degraded Images
arXiv paper abstract https://arxiv.org/abs/2406.09627
arXiv PDF paper https://arxiv.org/pdf/2406.09627
GitHub https://github.com/robustsam/RobustSAM
Project page https://robustsam.github.io
Segment Anything Model (SAM) … performance is challenged by images with degraded quality.
… propose the Robust Segment Anything Model (RobustSAM), which enhances SAM’s performance on low-quality images while preserving its promptability and zero-shot generalization.
… method leverages the pre-trained SAM model with only marginal parameter increments and computational requirements.
The additional parameters of RobustSAM can be optimized within 30 hours on eight GPUs, demonstrating its feasibility and practicality for typical research laboratories.
… RobustSAM’s superior performance, especially under zero-shot conditions, underscoring its potential for extensive real-world application.
… method has been shown to effectively improve the performance of SAM-based downstream tasks such as single image dehazing and deblurring.
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
