Related papers: Unfolding Once is Enough: A Deployment-Friendly Tr…

Untrained neural networks (UNNs) offer high-fidelity electromagnetic inverse scattering reconstruction but are computationally limited by high-dimensional spatial-domain optimization. We propose a Real-Time Physics-Driven Fourier-Spectral…

Image restoration is a challenging ill-posed problem which also has been a long-standing issue. In the past few years, the convolution neural networks (CNNs) almost dominated the computer vision and had achieved considerable success in…

Recent research on super-resolution has progressed with the development of deep convolutional neural networks (DCNN). In particular, residual learning techniques exhibit improved performance. In this paper, we develop an enhanced deep…

Deep neural networks ( DNNs ) are becoming a key enabling technology for many application domains. However, on-device inference on battery-powered, resource-constrained embedding systems is often infeasible due to prohibitively long…

Deep convolution Neural Network (DCNN) has been widely used in computer vision tasks. However, for edge devices even inference has too large computational complexity and data access amount. The inference latency of state-of-the-art models…

Efficient onboard multi-field sparse reconstruction is essential for the autonomous operation of aerospace vehicles. While existing deep learning models exhibit promise for single-field reconstruction, deploying multiple independent models…

Visual generative models (e.g., diffusion models) typically operate in compressed latent spaces to balance training efficiency and sample quality. In parallel, there has been growing interest in leveraging high-quality pre-trained visual…

Hybrid CNN-Transformer architectures achieve strong results in image super-resolution, but scaling attention windows or convolution kernels significantly increases computational cost, limiting deployment on resource-constrained devices. We…

Major efforts in data-driven image super-resolution (SR) primarily focus on expanding the receptive field of the model to better capture contextual information. However, these methods are typically implemented by stacking deeper networks or…

This paper proposes a novel Unified Feature Optimization (UFO) paradigm for training and deploying deep models under real-world and large-scale scenarios, which requires a collection of multiple AI functions. UFO aims to benefit each single…

Sinusoidal neural networks have been shown effective as implicit neural representations (INRs) of low-dimensional signals, due to their smoothness and high representation capacity. However, initializing and training them remain empirical…

Tapered optical fibers (TFs), with diameters gradually reduced from hundreds of microns to the micron scale, offer key advantages over conventional flat optical fibers (FFs), including uniform illumination, efficient long-range signal…

Deep Convolutional Neural Networks (DCNNs) have achieved impressive performance in Single Image Super-Resolution (SISR). To further improve the performance, existing CNN-based methods generally focus on designing deeper architecture of the…

For years, Single Image Super Resolution (SISR) has been an interesting and ill-posed problem in computer vision. The traditional super-resolution (SR) imaging approaches involve interpolation, reconstruction, and learning-based methods.…

This paper focuses on an accurate and fast interpolation approach for image transformation employed in the design of CNN architectures. Standard Spatial Transformer Networks (STNs) use bilinear or linear interpolation as their…

Visual Transformers have achieved great success in almost all vision tasks, such as classification, detection, and so on. However, the model complexity and the inference speed of the visual transformers hinder their deployments in…

Despite notable advancements in the field of computer vision, the precise detection of tiny objects continues to pose a significant challenge, largely owing to the minuscule pixel representation allocated to these objects in imagery data.…

Omnidirectional images (ODIs) have obtained lots of research interest for immersive experiences. Although ODIs require extremely high resolution to capture details of the entire scene, the resolutions of most ODIs are insufficient. Previous…

Due to the unaffordable size and intensive computation costs of low-level vision models, All-in-One models that are designed to address a handful of low-level vision tasks simultaneously have been popular. However, existing All-in-One…

Unknown Object Detection (UOD) aims to identify objects of unseen categories, differing from the traditional detection paradigm limited by the closed-world assumption. A key component of UOD is learning a generalized representation, i.e.…