Related papers: Perception-Distortion Trade-off in the SR Space Sp…
Text-to-image diffusion models are a class of deep generative models that have demonstrated an impressive capacity for high-quality image generation. However, these models are susceptible to implicit biases that arise from web-scale…
Generative Adversarial Networks (GANs) have shown great performance on super-resolution problems since they can generate more visually realistic images and video frames. However, these models often introduce side effects into the outputs,…
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…
Hyperspectral (HS) images contain detailed spectral information that has proven crucial in applications like remote sensing, surveillance, and astronomy. However, because of hardware limitations of HS cameras, the captured images have low…
3D object generation from a single image involves estimating the full 3D geometry and texture of unseen views from an unposed RGB image captured in the wild. Accurately reconstructing an object's complete 3D structure and texture has…
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…
Remote sensing images captured by different platforms exhibit significant disparities in spatial resolution. Large scale factor super-resolution (SR) algorithms are vital for maximizing the utilization of low-resolution (LR) satellite data…
Existing color-guided depth super-resolution (DSR) approaches require paired RGB-D data as training samples where the RGB image is used as structural guidance to recover the degraded depth map due to their geometrical similarity. However,…
Generative adversarial networks (GAN) and generative diffusion models (DM) have been widely used in real-world image super-resolution (Real-ISR) to enhance the image perceptual quality. However, these generative models are prone to…
Light field (LF) image super-resolution (SR) is a challenging problem due to its inherent ill-posed nature, where a single low-resolution (LR) input LF image can correspond to multiple potential super-resolved outcomes. Despite this…
Clean images are crucial for visual tasks such as small object detection, especially at high resolutions. However, real-world images are often degraded by adverse weather, and weather restoration methods may sacrifice high-frequency details…
High-resolution remote sensing images (RSIs) are crucial for Earth observation applications, yet acquiring them is often limited by sensor constraints and costs. In recent years, generative super-resolution (SR) methods, particularly…
Flow image super-resolution (FISR) aims at recovering high-resolution turbulent velocity fields from low-resolution flow images. Existing FISR methods mainly process the flow images in natural image patterns, while the critical and distinct…
The introduction of generative models has significantly advanced image super-resolution (SR) in handling real-world degradations. However, they often incur fidelity-related issues, particularly distorting textual structures. In this paper,…
Image retouching, aiming to regenerate the visually pleasing renditions of given images, is a subjective task where the users are with different aesthetic sensations. Most existing methods deploy a deterministic model to learn the…
In computer vision and image processing tasks, image fusion has evolved into an attractive research field. However, recent existing image fusion methods are mostly built on pixel-level operations, which may produce unacceptable artifacts…
Normalizing flow models have been used successfully for generative image super-resolution (SR) by approximating complex distribution of natural images to simple tractable distribution in latent space through Invertible Neural Networks…
Guidance techniques are commonly used in diffusion and flow models to improve image quality and input consistency for conditional generative tasks such as class-conditional and text-to-image generation. In particular, classifier-free…
Most learning-based super-resolution (SR) methods aim to recover high-resolution (HR) image from a given low-resolution (LR) image via learning on LR-HR image pairs. The SR methods learned on synthetic data do not perform well in…
Score distillation sampling (SDS) has proven to be an important tool, enabling the use of large-scale diffusion priors for tasks operating in data-poor domains. Unfortunately, SDS has a number of characteristic artifacts that limit its…