AI RESEARCH
Segment Any-Quality Images with Generative Latent Space Enhancement
arXiv CS.CV
•
ArXi:2503.12507v3 Announce Type: replace Despite their success, Segment Anything Models (SAMs) experience significant performance drops on severely degraded, low-quality images, limiting their effectiveness in real-world scenarios. To address this, we propose GleSAM, which utilizes Generative Latent space Enhancement to boost robustness on low-quality images, thus enabling generalization across various image qualities.