Related papers: Frequency Consistent Adaptation for Real World Sup…

Deep neural networks have exhibited remarkable performance in image super-resolution (SR) tasks by learning a mapping from low-resolution (LR) images to high-resolution (HR) images. However, the SR problem is typically an ill-posed problem…

Self-Supervised Learning (SSL) enables us to pre-train foundation models without costly labeled data. Among SSL methods, Contrastive Learning (CL) methods are better at obtaining accurate semantic representations in noise interference.…

Super-resolution (SR) techniques designed for real-world applications commonly encounter two primary challenges: generalization performance and restoration accuracy. We demonstrate that when methods are trained using complex, large-range…

Surveillance scenarios are prone to several problems since they usually involve low-resolution footage, and there is no control of how far the subjects may be from the camera in the first place. This situation is suitable for the…

Convolutional neural networks (CNNs) demonstrate excellent performance in various computer vision applications. In recent years, FPGA-based CNN accelerators have been proposed for optimizing performance and power efficiency. Most…

Single Image Super-Resolution (SISR) aims to generate a high-resolution (HR) image of a given low-resolution (LR) image. The most of existing convolutional neural network (CNN) based SISR methods usually take an assumption that a LR image…

We propose a simple yet effective model for Single Image Super-Resolution (SISR), by combining the merits of Residual Learning and Convolutional Sparse Coding (RL-CSC). Our model is inspired by the Learned Iterative Shrinkage-Threshold…

Retinal Optical Coherence Tomography Angiography (OCTA) with high-resolution is important for the quantification and analysis of retinal vasculature. However, the resolution of OCTA images is inversely proportional to the field of view at…

Self-supervised learning is crucial for super-resolution because ground-truth images are usually unavailable for real-world settings. Existing methods derive self-supervision from low-resolution images by creating pseudo-pairs or by…

Deep priors have emerged as potent methods in hyperspectral image (HSI) reconstruction. While most methods emphasize space-domain learning using image space priors like non-local similarity, frequency-domain learning using image frequency…

Deep learning-based blind super-resolution (SR) methods have recently achieved unprecedented performance in upscaling frames with unknown degradation. These models are able to accurately estimate the unknown downscaling kernel from a given…

While diffusion models have achieved state-of-the-art performance in Image Super-Resolution (SR), their prohibitive computational and memory demands restrict their training and inference to fixed-size inputs. The standard workaround to…

We present a highly accurate single-image super-resolution (SR) method. Our method uses a very deep convolutional network inspired by VGG-net used for ImageNet classification \cite{simonyan2015very}. We find increasing our network depth…

Medical Image-to-image translation is a key task in computer vision and generative artificial intelligence, and it is highly applicable to medical image analysis. GAN-based methods are the mainstream image translation methods, but they…

Despite achieving remarkable progress in recent years, single-image super-resolution methods are developed with several limitations. Specifically, they are trained on fixed content domains with certain degradations (whether synthetic or…

Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution as the limited sampling resources have to be shared with the angular dimension. LF spatial super-resolution (SR) thus becomes an indispensable…

Convolutional neural networks (CNN) have recently achieved remarkable successes in various image classification and understanding tasks. The deep features obtained at the top fully-connected layer of the CNN (FC-features) exhibit rich…

Synthetic data provide low-cost, accurately annotated samples for geometry-sensitive vision tasks, but appearance and imaging differences between synthetic and real domains cause severe domain shift and degrade downstream performance.…

Recent advances in unsupervised domain adaptation mainly focus on learning shared representations by global distribution alignment without considering class information across domains. The neglect of class information, however, may lead to…

Recent advances in unsupervised domain adaptation for semantic segmentation have shown great potentials to relieve the demand of expensive per-pixel annotations. However, most existing works address the domain discrepancy by aligning the…