Related papers: Can No-Reference Quality-Assessment Methods Serve …

Single-image super-resolution (SR) has achieved remarkable progress with deep learning, yet most approaches rely on distortion-oriented losses or heuristic perceptual priors, which often lead to a trade-off between fidelity and visual…

Deep learning methods for pansharpening have advanced rapidly, yet models pretrained on data from a specific sensor often generalize poorly to data from other sensors. Existing methods to tackle such cross-sensor degradation include…

Low-light image enhancement remains a challenging task, particularly in the absence of paired training data. In this study, we present LucentVisionNet, a novel zero-shot learning framework that addresses the limitations of traditional and…

Single image super-resolution (SR) aims to estimate a high-resolution (HR) image from a lowresolution (LR) input. Image priors are commonly learned to regularize the otherwise seriously ill-posed SR problem, either using external LR-HR…

Existing reference (RF)-based super-resolution (SR) models try to improve perceptual quality in SR under the assumption of the availability of high-resolution RF images paired with low-resolution (LR) inputs at testing. As the RF images…

Quality assessment of in-the-wild videos is a challenging problem because of the absence of reference videos and shooting distortions. Knowledge of the human visual system can help establish methods for objective quality assessment of…

We present an empirical analysis of the state-of-the-art systems for referring expression recognition -- the task of identifying the object in an image referred to by a natural language expression -- with the goal of gaining insight into…

While deep neural network (DNN)-based perception models are useful for many applications, these models are black boxes and their outputs are not yet well understood. To confidently enable a real-world, decision-making system to utilize such…

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…

Visual scenes are composed of visual concepts and have the property of combinatorial explosion. An important reason for humans to efficiently learn from diverse visual scenes is the ability of compositional perception, and it is desirable…

RGBD images, combining high-resolution color and lower-resolution depth from various types of depth sensors, are increasingly common. One can significantly improve the resolution of depth maps by taking advantage of color information; deep…

Recent advancements in Multimodal Large Language Models (MLLMs) have enabled them to effectively integrate vision and language, addressing a variety of downstream tasks. However, despite their significant success, these models still exhibit…

Recently, there has been a large amount of work towards fooling deep-learning-based classifiers, particularly for images, via adversarial inputs that are visually similar to the benign examples. However, researchers usually use Lp-norm…

We show that the influence of a subset of the training samples can be removed -- or "forgotten" -- from the weights of a network trained on large-scale image classification tasks, and we provide strong computable bounds on the amount of…

Generative super-resolution (GSR) currently sets the state-of-the-art in terms of perceptual image quality, overcoming the "regression-to-the-mean" blur of prior non-generative models. However, from a human perspective, such models do not…

Super-resolution without explicit sub-pixel motion estimation is a very active subject of image reconstruction containing general motion. The Non-Local Means (NLM) method is a simple image reconstruction method without explicit motion…

Contemporary deep learning models have achieved impressive performance in image classification by primarily leveraging statistical regularities within large datasets, but they rarely incorporate structured insights drawn directly from…

Purpose: Deep learning-based MRI artifact correction methods often demonstrate poor generalization to clinical data. This limitation largely stems from the inability of deep learning models in reliably distinguishing motion artifacts from…

Diffusion models are a powerful class of generative models capable of producing high-quality images from pure noise using a simple text prompt. While most methods which introduce additional spatial constraints into the generated images…

We present a no reference (NR) quality assessment algorithm for assessing the perceptual quality of natural stereoscopic 3D (S3D) videos. This work is inspired by our finding that the joint statistics of the subband coefficients of motion…