Related papers: EPNet: An Efficient Pyramid Network for Enhanced S…

We introduce Equivariant Neural Field Expectation Maximization (EFEM), a simple, effective, and robust geometric algorithm that can segment objects in 3D scenes without annotations or training on scenes. We achieve such unsupervised…

Parameter-Efficient Fine-Tuning (PEFT) has become a dominant paradigm for deploying LLMs in multi-task scenarios due to its extreme parameter efficiency. While Mixture-of-Experts (MoE) based LoRA variants have achieved promising results by…

Convolutional neural network (CNN) based methods have recently achieved great success for image super-resolution (SR). However, most deep CNN based SR models attempt to improve distortion measures (e.g. PSNR, SSIM, IFC, VIF) while resulting…

Deep convolutional neural networks have been demonstrated to be effective for SISR in recent years. On the one hand, residual connections and dense connections have been used widely to ease forward information and backward gradient flows to…

Deep convolutional neural networks (CNNs) have been widely applied for low-level vision over the past five years. According to nature of different applications, designing appropriate CNN architectures is developed. However, customized…

Single Image Super-Resolution (SISR) is a crucial task in low-level computer vision, aiming to reconstruct high-resolution images from low-resolution counterparts. Conventional attention mechanisms have significantly improved SISR…

This paper introduces Progressively Diffused Networks (PDNs) for unifying multi-scale context modeling with deep feature learning, by taking semantic image segmentation as an exemplar application. Prior neural networks, such as ResNet, tend…

Multi-modal fusion serves as a cornerstone for successful depth map super-resolution. However, commonly used fusion strategies, such as addition and concatenation, fall short of effectively bridging the modal gap. As a result, guided image…

In this paper, we focus on exploring effective methods for faster and accurate semantic segmentation. A common practice to improve the performance is to attain high-resolution feature maps with strong semantic representation. Two strategies…

Recent feature matching methods have achieved remarkable performance but lack efficiency consideration. In this paper, we revisit the mainstream detector-free matching pipeline and improve all its stages considering both accuracy and…

Efficient convolutional neural network (CNN) architecture design has attracted growing research interests. However, they typically apply single receptive field (RF), small asymmetric RFs, or pyramid RFs to learn different feature…

Deep convolutional neural networks (CNNs) with strong expressive ability have achieved impressive performances on single image super-resolution (SISR). However, their excessive amounts of convolutions and parameters usually consume high…

Semantic Segmentation plays a pivotal role in many applications related to medical image and video analysis. However, designing a neural network architecture for medical image and surgical video segmentation is challenging due to the…

Face Super-Resolution (FSR) aims to recover high-resolution (HR) face images from low-resolution (LR) ones. Despite the progress made by convolutional neural networks in FSR, the results of existing approaches are not ideal due to their low…

Pavement Distress Recognition (PDR) is an important step in pavement inspection and can be powered by image-based automation to expedite the process and reduce labor costs. Pavement images are often in high-resolution with a low ratio of…

Spatial resolution is a critical imaging parameter in magnetic resonance imaging (MRI). Acquiring high resolution MRI data usually takes long scanning time and would subject to motion artifacts due to hardware, physical, and physiological…

Remote sensing target detection aims to identify and locate critical targets within remote sensing images, finding extensive applications in agriculture and urban planning. Feature pyramid networks (FPNs) are commonly used to extract…

Deep learning based methods, especially convolutional neural networks (CNNs) have been successfully applied in the field of single image super-resolution (SISR). To obtain better fidelity and visual quality, most of existing networks are of…

Real-time semantic segmentation, which can be visually understood as the pixel-level classification task on the input image, currently has broad application prospects, especially in the fast-developing fields of autonomous driving and drone…

Single image super-resolution (SISR) is the process of obtaining one high-resolution version of a low-resolution image by increasing the number of pixels per unit area. This method has been actively investigated by the research community,…