Segment anything, from space?

S Ren, F Luzi, S Lahrichi, K Kassaw… - Proceedings of the …, 2024 - openaccess.thecvf.com
Recently, the first foundation model developed specifically for image segmentation tasks
was developed, termed the" Segment Anything Model"(SAM). SAM can segment objects in …

Distilling Semantic Priors from SAM to Efficient Image Restoration Models

Q Zhang, X Liu, W Li, H Chen, J Liu… - Proceedings of the …, 2024 - openaccess.thecvf.com
In image restoration (IR) leveraging semantic priors from segmentation models has been a
common approach to improve performance. The recent segment anything model (SAM) has …

Sam-deblur: Let segment anything boost image deblurring

S Li, M Liu, Y Zhang, S Chen, H Li… - ICASSP 2024-2024 …, 2024 - ieeexplore.ieee.org
Image deblurring is a critical task in the field of image restoration, aiming to eliminate
blurring artifacts. However, the challenge of addressing non-uniform blurring leads to an ill …

RobustSAM: Segment Anything Robustly on Degraded Images

WT Chen, YJ Vong, SY Kuo, S Ma… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract Segment Anything Model (SAM) has emerged as a transformative approach in
image segmentation acclaimed for its robust zero-shot segmentation capabilities and …

Transfer CLIP for Generalizable Image Denoising

J Cheng, D Liang, S Tan - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
Image denoising is a fundamental task in computer vision. While prevailing deep learning-
based supervised and self-supervised methods have excelled in eliminating in-distribution …

[PDF][PDF] Priors in Deep Image Restoration and Enhancement: A Survey

Y Lu, Y Lin, H Wu, Y Luo, X Zheng… - arXiv preprint arXiv …, 2022 - researchgate.net
Image restoration and enhancement is a process of improving the image quality by
removing degradations, such as noise, blur, and resolution degradation. Deep learning (DL) …

Cycle contrastive adversarial learning with structural consistency for unsupervised high-quality image deraining transformer

C Zhao, W Cai, C Hu, Z Yuan - Neural Networks, 2024 - Elsevier
In overcoming the challenges faced in adapting to paired real-world data, recent
unsupervised single image deraining (SID) methods have proven capable of accomplishing …

MAS-SAM: Segment Any Marine Animal with Aggregated Features

T Yan, Z Wan, X Deng, P Zhang, Y Liu, H Lu - arXiv preprint arXiv …, 2024 - arxiv.org
Recently, Segment Anything Model (SAM) shows exceptional performance in generating
high-quality object masks and achieving zero-shot image segmentation. However, as a …

Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning

M Li, T Li, G Wang, P Wang, Y Yang… - arXiv preprint arXiv …, 2024 - arxiv.org
In this study, we address the intricate challenge of multi-task dense prediction,
encompassing tasks such as semantic segmentation, depth estimation, and surface normal …

Low-light Image Enhancement with SAM-based Structure Priors and Guidance

G Li, B Zhao, X Li - IEEE Transactions on Multimedia, 2024 - ieeexplore.ieee.org
Low-light images often suffer from severe detail lost in darker areas and non-uniform
illumination distribution across distinct regions. Thus, structure modeling and region-specific …