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

Image inpainting plays a vital role in restoring missing image regions and supporting high-level vision tasks, but traditional methods struggle with complex textures and large occlusions. Although Transformer-based approaches have…

Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference, especially with long inputs due to the attention mechanism's memory overhead. We observe…

Image deblurring aims to recover the latent sharp image from its blurry counterpart and has a wide range of applications in computer vision. The Convolution Neural Networks (CNNs) have performed well in this domain for many years, and until…

One limitation of existing Transformer-based models is that they cannot handle very long sequences as input since their self-attention operations exhibit quadratic time and space complexity. This problem becomes especially acute when…

Complicated image registration is a key issue in medical image analysis, and deep learning-based methods have achieved better results than traditional methods. The methods include ConvNet-based and Transformer-based methods. Although…

Recently, in the super-resolution (SR) domain, transformers have outperformed CNNs with fewer FLOPs and fewer parameters since they can deal with long-range dependency and adaptively adjust weights based on instance. In this paper, we…

Deep learning techniques have achieved remarkable success in the semantic segmentation of remote sensing images and in land-use change detection. Nevertheless, their real-time deployment on edge platforms remains constrained by decoder…

Nowadays, transformer networks have demonstrated superior performance in many computer vision tasks. In a multi-view 3D reconstruction algorithm following this paradigm, self-attention processing has to deal with intricate image tokens…

Efficient and lightweight single-image super-resolution (SISR) has achieved remarkable performance in recent years. One effective approach is the use of large kernel designs, which have been shown to improve the performance of SISR models…

Convolutional Neural Networks have been the backbone of recent rapid progress in Single-Image Super-Resolution. However, existing networks are very deep with many network parameters, thus having a large memory footprint and being…

Previous works have shown that reducing parameter overhead and computations for transformer-based single image super-resolution (SISR) models (e.g., SwinIR) usually leads to a reduction of performance. In this paper, we present GRFormer, an…

Transform and entropy models are the two core components in deep image compression neural networks. Most existing learning-based image compression methods utilize convolutional-based transform, which lacks the ability to model long-range…

Diffusion models have recently achieved significant success in various image manipulation tasks, including image super-resolution and perceptual quality enhancement. Pretrained text-to-image models, such as Stable Diffusion, have exhibited…

We study on image super-resolution (SR), which aims to recover realistic textures from a low-resolution (LR) image. Recent progress has been made by taking high-resolution images as references (Ref), so that relevant textures can be…

How to aggregate spatial information plays an essential role in learning-based image restoration. Most existing CNN-based networks adopt static convolutional kernels to encode spatial information, which cannot aggregate spatial information…

The deep convolutional neural networks (CNNs)-based single image dehazing methods have achieved significant success. The previous methods are devoted to improving the network's performance by increasing the network's depth and width. The…

This paper proposes the first pure Transformer structure inversion network called SwinStyleformer, which can compensate for the shortcomings of the CNNs inversion framework by handling long-range dependencies and learning the global…

Single-image super-resolution (SISR) has achieved significant breakthroughs with the development of deep learning. However, these methods are difficult to be applied in real-world scenarios since they are inevitably accompanied by the…

In this paper, we introduce a new image representation based on a multilayer kernel machine. Unlike traditional kernel methods where data representation is decoupled from the prediction task, we learn how to shape the kernel with…

Semantic segmentation tasks naturally require high-resolution information for pixel-wise segmentation and global context information for class prediction. While existing vision transformers demonstrate promising performance, they often…