Related papers: HiTSR: A Hierarchical Transformer for Reference-ba…
Hyperspectral image (HSI) fusion addresses the challenge of reconstructing High-Resolution HSIs (HR-HSIs) from High-Resolution Multispectral images (HR-MSIs) and Low-Resolution HSIs (LR-HSIs), a critical task given the high costs and…
Modern diffusion models, particularly those utilizing a Transformer-based UNet for denoising, rely heavily on self-attention operations to manage complex spatial relationships, thus achieving impressive generation performance. However, this…
Methods based on convolutional neural network (CNN) have demonstrated tremendous improvements on single image super-resolution. However, the previous methods mainly restore images from one single area in the low resolution (LR) input, which…
In computer vision, Single Image Super-Resolution (SISR) is still a difficult problem. We present ViT-SR, a new technique to improve the performance of a Vision Transformer (ViT) employing a two-stage training strategy. In our method, the…
Advanced diffusion models (DMs) perform impressively in image super-resolution (SR), but the high memory and computational costs hinder their deployment. Binarization, an ultra-compression algorithm, offers the potential for effectively…
In the last few years, several deep learning models, especially Generative Adversarial Networks have received a lot of attention for the task of Single Image Super-Resolution (SISR). These methods focus on building an end-to-end framework,…
Transformer-based models have achieved remarkable results in low-level vision tasks including image super-resolution (SR). However, early Transformer-based approaches that rely on self-attention within non-overlapping windows encounter…
Existing diffusion-based super-resolution approaches often exhibit semantic ambiguities due to inaccuracies and incompleteness in their text conditioning, coupled with the inherent tendency for cross-attention to divert towards irrelevant…
We propose Diverse Restormer (DART), a novel image restoration method that effectively integrates information from various sources (long sequences, local and global regions, feature dimensions, and positional dimensions) to address…
Multi-scale inference is commonly used to improve the results of semantic segmentation. Multiple images scales are passed through a network and then the results are combined with averaging or max pooling. In this work, we present an…
Reference-based image super-resolution (RefSR) is a promising SR branch and has shown great potential in overcoming the limitations of single image super-resolution. While previous state-of-the-art RefSR methods mainly focus on improving…
Video super-resolution, which aims at producing a high-resolution video from its corresponding low-resolution version, has recently drawn increasing attention. In this work, we propose a novel method that can effectively incorporate…
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…
To solve the ill-posed problem of hyperspectral image super-resolution (HSISR), an usually method is to use the prior information of the hyperspectral images (HSIs) as a regularization term to constrain the objective function. Model-based…
With the popularity of Transformer architectures in computer vision, the research focus has shifted towards developing computationally efficient designs. Window-based local attention is one of the major techniques being adopted in recent…
Spiking Transformers, which integrate Spiking Neural Networks (SNNs) with Transformer architectures, have attracted significant attention due to their potential for energy efficiency and high performance. However, existing models in this…
Although video summarization has achieved tremendous success benefiting from Recurrent Neural Networks (RNN), RNN-based methods neglect the global dependencies and multi-hop relationships among video frames, which limits the performance.…
Recently, deep learning based single image super-resolution(SR) approaches have achieved great development. The state-of-the-art SR methods usually adopt a feed-forward pipeline to establish a non-linear mapping between low-res(LR) and…
As intensities of MRI volumes are inconsistent across institutes, it is essential to extract universal features of multi-modal MRIs to precisely segment brain tumors. In this concept, we propose a volumetric vision transformer that follows…
Incorporating heterogeneous representations from different architectures has facilitated various vision tasks, e.g., some hybrid networks combine transformers and convolutions. However, complementarity between such heterogeneous…