Related papers: Edge-Efficient Image Restoration: Transformer Dist…

Convolutional neural network (CNN) based image enhancement methods such as super-resolution and detail enhancement have achieved remarkable performances. However, amounts of operations including convolution and parameters within the…

All-in-One image restoration aims to address multiple image degradation problems using a single model, offering a more practical and versatile solution compared to designing dedicated models for each degradation type. Existing approaches…

Hyperspectral change detection plays an essential role of monitoring the dynamic urban development and detecting precise fine object evolution and alteration. In this paper, we have proposed an original Efficient Multi-temporal…

Designing low-latency and high-efficiency hybrid networks for a variety of low-cost commodity edge devices is both costly and tedious, leading to the adoption of hardware-aware neural architecture search (NAS) for finding optimal…

Deep state-space models (SSMs), like recent Mamba architectures, are emerging as a promising alternative to CNN and Transformer networks. Existing Mamba-based restoration methods process visual data by leveraging a flatten-and-scan strategy…

Long-sequence state-space models (SSMs) such as Hyena and Mamba replace the quadratic complexity of self-attention with more efficient FFT and scan operations. However, modern accelerators like GPUs are poorly suited to these non-GEMM…

Recent efforts on image restoration have focused on developing "all-in-one" models that can handle different degradation types and levels within single model. However, most of mainstream Transformer-based ones confronted with dilemma…

This paper proposes an end-to-end Efficient Re-parameterizationResidual Attention Network(ERRA-Net) to directly restore the nonhomogeneous hazy image. The contribution of this paper mainly has the following three aspects: 1) A novel…

Optical and Synthetic Aperture Radar (SAR) image registration is crucial for multi-modal image fusion and applications. However, several challenges limit the performance of existing deep learning-based methods in cross-modal image…

State-space models (SSMs) have recently shown promise in capturing long-range dependencies with subquadratic computational complexity, making them attractive for various applications. However, purely SSM-based models face critical…

In recent years, Transformer-based language models have become the standard approach for natural language processing tasks. However, stringent throughput and latency requirements in industrial applications are limiting their adoption. To…

Hybrid models combining Transformers and State Space Models (SSMs) are promising for balancing performance and efficiency. However, optimizing these hybrid models, particularly by addressing the potential redundancy inherent within the…

We introduce the first learning-based dense matching algorithm, termed Equirectangular Projection-Oriented Dense Kernelized Feature Matching (EDM), specifically designed for omnidirectional images. Equirectangular projection (ERP) images,…

Effectively modeling global context information in hyperspectral image (HSI) denoising is crucial, but prevailing methods using convolution or transformers still face localized or computational efficiency limitations. Inspired by the…

While deep neural networks (NN) significantly advance image compressed sensing (CS) by improving reconstruction quality, the necessity of training current CS NNs from scratch constrains their effectiveness and hampers rapid deployment.…

Unlike general image deblurring that prioritizes perceptual quality, QR code deblurring focuses on ensuring successful decoding. QR codes are characterized by highly structured patterns with sharp edges, a robust prior for restoration. Yet…

Reconfigurable electromagnetic structures (REMSs), such as reconfigurable reflectarrays (RRAs) or reconfigurable intelligent surfaces (RISs), hold significant potential to improve the spectral efficiency of wireless communication systems…

Transformer architectures deliver state-of-the-art accuracy via dense full-attention, but their quadratic time and memory complexity with respect to sequence length limits practical deployment. Linear attention mechanisms offer linear or…

Image restoration aims to recover details and enhance contrast in degraded images. With the growing demand for high-quality imaging (\textit{e.g.}, 4K and 8K), achieving a balance between restoration quality and computational efficiency has…

Transformers have revolutionized image modeling tasks with adaptations like DeIT, Swin, SVT, Biformer, STVit, and FDVIT. However, these models often face challenges with inductive bias and high quadratic complexity, making them less…