Related papers: From Coarse to Fine: Hierarchical Pixel Integratio…

Convolutional neural network (CNN) has achieved great success on image super-resolution (SR). However, most deep CNN-based SR models take massive computations to obtain high performance. Downsampling features for multi-resolution fusion is…

Recently, transformer-based methods have demonstrated impressive results in various vision tasks, including image super-resolution (SR), by exploiting the self-attention (SA) for feature extraction. However, the computation of SA in most…

Super-resolution (SR) is a coveted image processing technique for mobile apps ranging from the basic camera apps to mobile health. Existing SR algorithms rely on deep learning models with significant memory requirements, so they have yet to…

Semantic segmentation is the task of classifying each pixel in an image. Training a segmentation model achieves best results using annotated images, where each pixel is annotated with the corresponding class. When obtaining fine annotations…

Pansharpening is to fuse a multispectral image (MSI) of low-spatial-resolution (LR) but rich spectral characteristics with a panchromatic image (PAN) of high-spatial-resolution (HR) but poor spectral characteristics. Traditional methods…

Recently, Convolutional Neural Networks (CNN) based image super-resolution (SR) have shown significant success in the literature. However, these methods are implemented as single-path stream to enrich feature maps from the input for the…

Superpixel-based image classification has traditionally leveraged graph neural networks (GNNs) for processing irregular image representations. Recent advances in computer vision, driven by Vision Transformers (ViTs), have introduced new…

Image super-resolution generation aims to generate a high-resolution image from its low-resolution image. However, more complex neural networks bring high computational costs and memory storage. It is still an active area for offering the…

There has recently been significant interest in training reinforcement learning (RL) agents in vision-based environments. This poses many challenges, such as high dimensionality and the potential for observational overfitting through…

Image super-resolution is a process to enhance image resolution. It is widely used in medical imaging, satellite imaging, target recognition, etc. In this paper, we conduct continuous modeling and assume that the unknown image intensity…

Convolutions (Convs) and multi-head self-attentions (MHSAs) are typically considered alternatives to each other for building vision backbones. Although some works try to integrate both, they apply the two operators simultaneously at the…

High-quality image captions play a crucial role in improving the performance of cross-modal applications such as text-to-image generation, text-to-video generation, and text-image retrieval. To generate long-form, high-quality captions,…

Convolutional neural networks (CNNs) have demonstrated superior performance in super-resolution (SR). However, most CNN-based SR methods neglect the different importance among feature channels or fail to take full advantage of the…

Global context information is vital in visual understanding problems, especially in pixel-level semantic segmentation. The mainstream methods adopt the self-attention mechanism to model global context information. However, pixels belonging…

Convolutional Neural Networks (CNNs) have significantly advanced Image Super-Resolution (SR), yet most CNN-based methods rely solely on pixel-based transformations, often leading to artifacts and blurring, particularly under severe…

An event camera detects per-pixel intensity difference and produces asynchronous event stream with low latency, high dynamic range, and low power consumption. As a trade-off, the event camera has low spatial resolution. We propose an…

Deep convolutional networks have attracted great attention in image restoration and enhancement. Generally, restoration quality has been improved by building more and more convolutional block. However, these methods mostly learn a specific…

Recent attention has been devoted to the pursuit of learning semantic segmentation models exclusively from image tags, a paradigm known as image-level Weakly Supervised Semantic Segmentation (WSSS). Existing attempts adopt the Class…

In the recent years impressive advances were made for single image super-resolution. Deep learning is behind a big part of this success. Deep(er) architecture design and external priors modeling are the key ingredients. The internal…

High-resolution LiDAR data plays a critical role in 3D semantic segmentation for autonomous driving, but the high cost of advanced sensors limits large-scale deployment. In contrast, low-cost sensors such as 16-channel LiDAR produce sparse…