Related papers: Dual-Path Learning based on Frequency Structural D…
Hyperspectral image produces high spectral resolution at the sacrifice of spatial resolution. Without reducing the spectral resolution, improving the resolution in the spatial domain is a very challenging problem. Motivated by the discovery…
Self-supervised video denoising methods typically extend image-based frameworks into the temporal dimension, yet they often struggle to integrate inter-frame temporal consistency with intra-frame spatial specificity. Existing Video…
Single Image Reflection Separation (SIRS) disentangles mixed images into transmission and reflection layers. Existing methods suffer from transmission-reflection confusion under nonlinear mixing, particularly in deep decoder layers, due to…
The state-of-the-art in discriminative unsupervised surface anomaly detection relies on external datasets for synthesizing anomaly-augmented training images. Such approaches are prone to failure on near-in-distribution anomalies since these…
In this work, we introduce a challenging image restoration task, referred to as SuperInpaint, which aims to reconstruct missing regions in low-resolution images and generate completed images with arbitrarily higher resolutions. We have…
SDF-based differential rendering frameworks have achieved state-of-the-art multiview 3D shape reconstruction. In this work, we re-examine this family of approaches by minimally reformulating its core appearance model in a way that…
Real-world image super-resolution is particularly challenging for diffusion models because real degradations are complex, heterogeneous, and rarely modeled explicitly. We propose a degradation-aware and structure-preserving diffusion…
Different from traditional image super-resolution task, real image super-resolution(Real-SR) focus on the relationship between real-world high-resolution(HR) and low-resolution(LR) image. Most of the traditional image SR obtains the LR…
We introduce Frequency Domain Perceptual Loss (FDPL), a loss function for single image super resolution (SR). Unlike previous loss functions used to train SR models, which are all calculated in the pixel (spatial) domain, FDPL is computed…
Real-world image super-resolution (RISR) has received increased focus for improving the quality of SR images under unknown complex degradation. Existing methods rely on the heavy SR models to enhance low-resolution (LR) images of different…
A number of reconstruction methods have been proposed recently for accelerated functional Magnetic Resonance Imaging (fMRI) data collection. However, existing methods suffer with the challenge of greater artifacts at high acceleration…
Multi-contrast magnetic resonance imaging (MRI) super-resolution intends to reconstruct high-resolution (HR) images from low-resolution (LR) scans by leveraging structural information present in HR reference images acquired with different…
Thermal infrared image enhancement aims to restore high-quality images from complex compound degradations. Existing all-in-one approaches typically employ a single shared backbone to handle diverse degradations, which causes gradient…
The outstanding pattern recognition performance of deep learning brings new vitality to the synthetic aperture radar (SAR) automatic target recognition (ATR). However, there is a limitation in current deep learning based ATR solution that…
Recognizing characters from low-resolution (LR) text images poses a significant challenge due to the information deficiency as well as the noise and blur in low-quality images. Current solutions for low-resolution text recognition (LTR)…
Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions. Existing HD-IR approaches usually ignore the inherent interference among hybrid distortions which compromises…
Dual-energy computed tomography (DECT) enables material-specific imaging through acquisitions at two different X-ray energy spectra. Material decomposition from DECT data is an ill-posed inverse problem that is highly sensitive to noise…
Recently, convolutional neural networks have shown promising performance for single-image super-resolution. In this paper, we propose Deep Artifact-Free Residual (DAFR) network which uses the merits of both residual learning and usage of…
3D volumetric reconstruction from incomplete or noisy measurements is a fundamental problem in medical imaging and computational tomography. Deep image prior (DIP)-based methods have recently shown strong capability for solving inverse…
Knowledge distillation is an effective and hardware-friendly method, which plays a key role in lightweighting remote sensing object detection. However, existing distillation methods often encounter the issue of mixed features in remote…