Related papers: Incorporating Degradation Estimation in Light Fiel…
Existing methods for single image super-resolution (SR) are typically evaluated with synthetic degradation models such as bicubic or Gaussian downsampling. In this paper, we investigate SR from the perspective of camera lenses, named as…
Blind face restoration (BFR) is fundamentally challenged by the extensive range of degradation types and degrees that impact model generalization. Recent advancements in diffusion models have made considerable progress in this field.…
Depth estimation under adverse conditions remains a significant challenge. Recently, multi-spectral depth estimation, which integrates both visible light and thermal images, has shown promise in addressing this issue. However, existing…
Recent efforts have witnessed remarkable progress in Satellite Video Super-Resolution (SVSR). However, most SVSR methods usually assume the degradation is fixed and known, e.g., bicubic downsampling, which makes them vulnerable in…
Novel view synthesis from low-light, noisy, and motion-blurred imagery remains a valuable and challenging task. Current volumetric rendering methods struggle with compound degradation, and sequential 2D preprocessing introduces artifacts…
Blind face restoration usually synthesizes degraded low-quality data with a pre-defined degradation model for training, while more complex cases could happen in the real world. This gap between the assumed and actual degradation hurts the…
Low-light image enhancement remains a challenging problem due to severe noise, color distortion, contrast degradation, and loss of structural details under insufficient illumination. Existing methods typically apply uniform enhancement…
While researches on model-based blind single image super-resolution (SISR) have achieved tremendous successes recently, most of them do not consider the image degradation sufficiently. Firstly, they always assume image noise obeys an…
Unsupervised real-world super-resolution (SR) faces critical challenges due to the complex, unknown degradation distributions in practical scenarios. Existing methods struggle to generalize from synthetic low-resolution (LR) and…
Compared to CNN-based methods, Transformer-based methods achieve impressive image restoration outcomes due to their abilities to model remote dependencies. However, how to apply Transformer-based methods to the field of blind…
Real-world stereo image super-resolution has a significant influence on enhancing the performance of computer vision systems. Although existing methods for single-image super-resolution can be applied to improve stereo images, these methods…
This paper presents a novel and interpretable end-to-end learning framework, called the deep compensation unfolding network (DCUNet), for restoring light field (LF) images captured under low-light conditions. DCUNet is designed with a…
Recently, most of state-of-the-art single image super-resolution (SISR) methods have attained impressive performance by using deep convolutional neural networks (DCNNs). The existing SR methods have limited performance due to a fixed…
We introduce deep-field metacalibration, a new technique that reduces the pixel noise in metacalibration estimators of weak lensing shear signals by using a deeper imaging survey for calibration. In standard metacalibration, when estimating…
End-to-end text spotting has attached great attention recently due to its benefits on global optimization and high maintainability for real applications. However, the input scale has always been a tough trade-off since recognizing a small…
Recent RGB-guided depth super-resolution methods have achieved impressive performance under the assumption of fixed and known degradation (e.g., bicubic downsampling). However, in real-world scenarios, captured depth data often suffer from…
While burst LR images are useful for improving the SR image quality compared with a single LR image, prior SR networks accepting the burst LR images are trained in a deterministic manner, which is known to produce a blurry SR image. In…
Recently, numerous algorithms have been developed to tackle the problem of light field super-resolution (LFSR), i.e., super-resolving low-resolution light fields to gain high-resolution views. Despite delivering encouraging results, these…
Synthetic high-resolution (HR) \& low-resolution (LR) pairs are widely used in existing super-resolution (SR) methods. To avoid the domain gap between synthetic and test images, most previous methods try to adaptively learn the synthesizing…
Restoring a sharp light field image from its blurry input has become essential due to the increasing popularity of parallax-based image processing. State-of-the-art blind light field deblurring methods suffer from several issues such as…