Related papers: GRFormer: Grouped Residual Self-Attention for Ligh…
The presence of residual and dense neural networks which greatly promotes the development of image Super-Resolution(SR) have witnessed a lot of impressive results. Depending on our observation, although more layers and connections could…
Recently, image restoration transformers have achieved comparable performance with previous state-of-the-art CNNs. However, how to efficiently leverage such architectures remains an open problem. In this work, we present Dual-former whose…
Image super-resolution reconstruction is an important task in the field of image processing technology, which can restore low resolution image to high quality image with high resolution. In recent years, deep learning has been applied in…
Self-attention has become a defacto choice for capturing global context in various vision applications. However, its quadratic computational complexity with respect to image resolution limits its use in real-time applications, especially…
Magnetic resonance images (MRI) acquired with low through-plane resolution compromise time and cost. The poor resolution in one orientation is insufficient to meet the requirement of high resolution for early diagnosis of brain disease and…
Single hyperspectral image super-resolution (single-HSI-SR) aims to restore a high-resolution hyperspectral image from a low-resolution observation. However, the prevailing CNN-based approaches have shown limitations in building long-range…
Transformer-based networks have achieved strong performance in low-level vision tasks like image deraining by utilizing spatial or channel-wise self-attention. However, irregular rain patterns and complex geometric overlaps challenge…
Prior dual-stream methods with the feature interaction mechanism have achieved remarkable performance in single image reflection removal (SIRR). However, they often struggle with (1) semantic understanding gap between the features of…
Single Image Super-resolution (SISR) produces high-resolution images with fine spatial resolutions from aremotely sensed image with low spatial resolution. Recently, deep learning and generative adversarial networks(GANs) have made…
Spiking Neural Networks have attracted significant attention in recent years due to their distinctive low-power characteristics. Meanwhile, Transformer models, known for their powerful self-attention mechanisms and parallel processing…
Recently Transformer-based hyperspectral image (HSI) change detection methods have shown remarkable performance. Nevertheless, existing attention mechanisms in Transformers have limitations in local feature representation. To address this…
Transformer models have recently garnered significant attention in image restoration due to their ability to capture long-range pixel dependencies. However, long-range attention often results in computational overhead without practical…
Medical image restoration tasks aim to recover high-quality images from degraded observations, exhibiting emergent desires in many clinical scenarios, such as low-dose CT image denoising, MRI super-resolution, and MRI artifact removal.…
Learning representations on large graphs is a long-standing challenge due to the inter-dependence nature. Transformers recently have shown promising performance on small graphs thanks to its global attention for capturing all-pair…
Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Transformer hinders its applicability to high-resolution images. Existing methods mitigate this…
Change detection (CD) in remote sensing aims to identify semantic differences between satellite images captured at different times. While deep learning has significantly advanced this field, existing approaches based on convolutional neural…
In recent years, deep neural networks, including Convolutional Neural Networks, Transformers, and State Space Models, have achieved significant progress in Remote Sensing Image (RSI) Super-Resolution (SR). However, existing SR methods…
Super-resolution (SR) is the technique of increasing the nominal resolution of image / video content accompanied with quality improvement. Video super-resolution (VSR) can be considered as the generalization of single image super-resolution…
Modern single image super-resolution (SISR) system based on convolutional neural networks (CNNs) achieves fancy performance while requires huge computational costs. The problem on feature redundancy is well studied in visual recognition…
In recent years, self-attention has become the dominant paradigm for sequence modeling in a variety of domains. However, in domains with very long sequence lengths the $\mathcal{O}(T^2)$ memory and $\mathcal{O}(T^2 H)$ compute costs can…