Related papers: Self-Calibrated Efficient Transformer for Lightwei…
Single image super-resolution (SISR) has witnessed great strides with the development of deep learning. However, most existing studies focus on building more complex networks with a massive number of layers. Recently, more and more…
In recent years, deep learning methods have been successfully applied to single-image super-resolution tasks. Despite their great performances, deep learning methods cannot be easily applied to real-world applications due to the requirement…
Recently, Transformer-based methods have achieved impressive results in single image super-resolution (SISR). However, the lack of locality mechanism and high complexity limit their application in the field of super-resolution (SR). To…
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…
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…
We present ASSET, a neural architecture for automatically modifying an input high-resolution image according to a user's edits on its semantic segmentation map. Our architecture is based on a transformer with a novel attention mechanism.…
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…
Recent progress in single-image super-resolution (SISR) has achieved remarkable performance, yet the computational costs of these methods remain a challenge for deployment on resource-constrained devices. In particular, transformer-based…
Transformer and its variants have shown state-of-the-art results in many vision tasks recently, ranging from image classification to dense prediction. Despite of their success, limited work has been reported on improving the model…
The dot product self-attention (DPSA) is a fundamental component of transformers. However, scaling them to long sequences, like documents or high-resolution images, becomes prohibitively expensive due to quadratic time and memory…
Since context modeling is critical for estimating depth from a single image, researchers put tremendous effort into obtaining global context. Many global manipulations are designed for traditional CNN-based architectures to overcome the…
This paper investigates two techniques for developing efficient self-supervised vision transformers (EsViT) for visual representation learning. First, we show through a comprehensive empirical study that multi-stage architectures with…
Hyperspectral imaging (HSI) is essential across various disciplines for its capacity to capture rich spectral information. However, efficiently reconstructing hyperspectral images from compressive sensing measurements presents significant…
Transformers have achieved remarkable results in single-image super-resolution (SR). However, the challenge of balancing model performance and complexity has hindered their application in lightweight SR (LSR). To tackle this challenge, we…
Single Image Super-Resolution (SISR) is a vital technique for improving the visual quality of low-resolution images. While recent deep learning models have made significant advancements in SISR, they often encounter computational challenges…
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…
Deep neural networks have demonstrated highly competitive performance in super-resolution (SR) for natural images by learning mappings from low-resolution (LR) to high-resolution (HR) images. However, hyperspectral super-resolution remains…
Single Image Super-Resolution (SISR) is a fundamental computer vision task that aims to reconstruct a high-resolution (HR) image from a low-resolution (LR) input. Transformer-based methods have achieved remarkable performance by modeling…
Transformer-based approaches have revolutionized image super-resolution by modeling long-range dependencies. However, the quadratic computational complexity of vanilla self-attention mechanisms poses significant challenges, often leading to…
Single image super resolution is a very important computer vision task, with a wide range of applications. In recent years, the depth of the super-resolution model has been constantly increasing, but with a small increase in performance, it…