Related papers: LKFormer: Large Kernel Transformer for Infrared Im…

The success of self-attention (SA) in Transformer demonstrates the importance of non-local information to image super-resolution (SR), but the huge computing power required makes it difficult to implement lightweight models. To solve this…

Medical image segmentation has seen significant improvements with transformer models, which excel in grasping far-reaching contexts and global contextual information. However, the increasing computational demands of these models,…

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…

Image super-resolution (SR) in resource-constrained scenarios demands lightweight models balancing performance and latency. Convolutional neural networks (CNNs) offer low latency but lack non-local feature capture, while Transformers excel…

Attention mechanisms have significantly advanced visual models by capturing global context effectively. However, their reliance on large-scale datasets and substantial computational resources poses challenges in data-scarce and…

Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods used a subset of combinations of component functions and weight matrices within the random feature paradigm. We…

Transformers have emerged as viable alternatives to convolutional neural networks owing to their ability to learn non-local region relationships in the spatial domain. The self-attention mechanism of the transformer enables transformers to…

Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoration and related tasks. Recently, another class of neural…

Hyperspectral image has become increasingly crucial due to its abundant spectral information. However, It has poor spatial resolution with the limitation of the current imaging mechanism. Nowadays, many convolutional neural networks have…

In the field of multi-organ medical image segmentation, recent methods frequently employ Transformers to capture long-range dependencies from image features. However, these methods overlook the high computational cost of Transformers and…

General-purpose super-resolution models, particularly Vision Transformers, have achieved remarkable success but exhibit fundamental inefficiencies in common infrared imaging scenarios like surveillance and autonomous driving, which operate…

Image generation has been successfully cast as an autoregressive sequence generation or transformation problem. Recent work has shown that self-attention is an effective way of modeling textual sequences. In this work, we generalize a…

In this paper, we propose LSRNA, a novel framework for higher-resolution (exceeding 1K) image generation using diffusion models by leveraging super-resolution directly in the latent space. Existing diffusion models struggle with scaling…

Matching visible and near-infrared (NIR) images remains a significant challenge in remote sensing image fusion. The nonlinear radiometric differences between heterogeneous remote sensing images make the image matching task even more…

We introduce a novel generative framework for functions by integrating Implicit Neural Representations (INRs) and Transformer-based hypernetworks into latent variable models. Unlike prior approaches that rely on MLP-based hypernetworks with…

In recent years, transformer-based methods have achieved remarkable progress in medical image segmentation due to their superior ability to capture long-range dependencies. However, these methods typically suffer from two major limitations.…

Objective image quality evaluation is a challenging task, which aims to measure the quality of a given image automatically. According to the availability of the reference images, there are Full-Reference and No-Reference IQA tasks,…

In the field of computer vision, visible light images often exhibit low contrast in low-light conditions, presenting a significant challenge. While infrared imagery provides a potential solution, its utilization entails high costs and…

The single image super-resolution(SISR) algorithms under deep learning currently have two main models, one based on convolutional neural networks and the other based on Transformer. The former uses the stacking of convolutional layers with…

Benefiting from powerful convolutional neural networks (CNNs), learning-based image inpainting methods have made significant breakthroughs over the years. However, some nature of CNNs (e.g. local prior, spatially shared parameters) limit…