Related papers: Evaluating and Preserving High-level Fidelity in S…
Speech super-resolution (SR) is the task that restores high-resolution speech from low-resolution input. Existing models employ simulated data and constrained experimental settings, which limit generalization to real-world SR. Predictive…
In this work, we investigate the understudied effect of the training data used for image super-resolution (SR). Most commonly, novel SR methods are developed and benchmarked on common training datasets such as DIV2K and DF2K. However, we…
Super-resolution (SR) is a technique that allows increasing the resolution of a given image. Having applications in many areas, from medical imaging to consumer electronics, several SR methods have been proposed. Currently, the best…
Super-resolution (SR) is a promising tool for generating high-fidelity simulations of physical systems from low-resolution data, enabling fast and accurate predictions in engineering applications. However, existing deep-learning based SR…
Many super-resolution (SR) models are optimized for high performance only and therefore lack efficiency due to large model complexity. As large models are often not practical in real-world applications, we investigate and propose novel loss…
Flow-based super-resolution (SR) models have demonstrated astonishing capabilities in generating high-quality images. However, these methods encounter several challenges during image generation, such as grid artifacts, exploding inverses,…
Existing real-world super-resolution (RSR) methods based on generative priors have achieved remarkable progress in producing high-quality and globally consistent reconstructions. However, they often struggle to recover fine-grained details…
Convolutional Neural Networks (CNNs) have achieved impressive results across many super-resolution (SR) and image restoration tasks. While many such networks can upscale low-resolution (LR) images using just the raw pixel-level information,…
Real-world Super-Resolution (Real-SR) methods focus on dealing with diverse real-world images and have attracted increasing attention in recent years. The key idea is to use a complex and high-order degradation model to mimic real-world…
Despite the plethora of successful Super-Resolution Reconstruction (SRR) models applied to natural images, their application to remote sensing imagery tends to produce poor results. Remote sensing imagery is often more complicated than…
Capturing ground truth data to benchmark super-resolution (SR) is challenging. Therefore, current quantitative studies are mainly evaluated on simulated data artificially sampled from ground truth images. We argue that such evaluations…
Traditionally, the main focus of image super-resolution techniques is on recovering the most likely high-quality images from low-quality images, using a one-to-one low- to high-resolution mapping. Proceeding that way, we ignore the fact…
3D super-resolution aims to reconstruct high-fidelity 3D models from low-resolution (LR) multi-view images. Early studies primarily focused on single-image super-resolution (SISR) models to upsample LR images into high-resolution images.…
Multimodal image super-resolution (SR) is the reconstruction of a high resolution image given a low-resolution observation with the aid of another image modality. While existing deep multimodal models do not incorporate domain knowledge…
Generative image reconstruction algorithms such as measurement conditioned diffusion models are increasingly popular in the field of medical imaging. These powerful models can transform low signal-to-noise ratio (SNR) inputs into outputs…
We introduce a new learning strategy for image enhancement by recurrently training the same simple superresolution (SR) network multiple times. After initially training an SR network by using pairs of a corrupted low resolution (LR) image…
Contemporary face hallucination (FH) models exhibit considerable ability to reconstruct high-resolution (HR) details from low-resolution (LR) face images. This ability is commonly learned from examples of corresponding HR-LR image pairs,…
The screen content images (SCIs) usually comprise various content types with sharp edges, in which the artifacts or distortions can be well sensed by the vanilla structure similarity measurement in a full reference manner. Nonetheless,…
Reinforcement learning (RL) has emerged as a promising paradigm for enhancing image editing and text-to-image (T2I) generation. However, current reward models, which act as critics during RL, often suffer from hallucinations and assign…
Real-world Super-Resolution (SR) has been traditionally tackled by first learning a specific degradation model that resembles the noise and corruption artifacts in low-resolution imagery. Thus, current methods lack generalization and lose…