Segment Any-Quality Images with Generative Latent Space Enhancement
This addresses a practical limitation for users of SAMs in real-world scenarios where image quality varies, though it is incremental as it builds on existing SAM frameworks.
The paper tackles the problem of Segment Anything Models (SAMs) experiencing performance drops on low-quality images by proposing GleSAM, which uses generative latent space enhancement to boost robustness, resulting in significant improvements on complex degradations while maintaining generalization to clear images.
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. Specifically, we adapt the concept of latent diffusion to SAM-based segmentation frameworks and perform the generative diffusion process in the latent space of SAM to reconstruct high-quality representation, thereby improving segmentation. Additionally, we introduce two techniques to improve compatibility between the pre-trained diffusion model and the segmentation framework. Our method can be applied to pre-trained SAM and SAM2 with only minimal additional learnable parameters, allowing for efficient optimization. We also construct the LQSeg dataset with a greater diversity of degradation types and levels for training and evaluating the model. Extensive experiments demonstrate that GleSAM significantly improves segmentation robustness on complex degradations while maintaining generalization to clear images. Furthermore, GleSAM also performs well on unseen degradations, underscoring the versatility of our approach and dataset.