Related papers: Region-aware Adaptive Instance Normalization for I…
Atmospheric turbulence, a common phenomenon in daily life, is primarily caused by the uneven heating of the Earth's surface. This phenomenon results in distorted and blurred acquired images or videos and can significantly impact downstream…
This paper provides an efficient training-free painterly image harmonization (PIH) method, dubbed FreePIH, that leverages only a pre-trained diffusion model to achieve state-of-the-art harmonization results. Unlike existing methods that…
Utilizing the trained model under different conditions without data annotation is attractive for robot applications. Towards this goal, one class of methods is to translate the image style from another environment to the one on which models…
The task of transforming a furnished room image into a background-only is extremely challenging since it requires making large changes regarding the scene context while still preserving the overall layout and style. In order to acquire…
Recent works on image harmonization solve the problem as a pixel-wise image translation task via large autoencoders. They have unsatisfactory performances and slow inference speeds when dealing with high-resolution images. In this work, we…
Image restoration is the task of recovering a clean image from a degraded version. In most cases, the degradation is spatially varying, and it requires the restoration network to both localize and restore the affected regions. In this…
Regional facial image synthesis conditioned on semantic mask has achieved great success using generative adversarial networks. However, the appearance of different regions may be inconsistent with each other when conducting regional image…
Synthetic images created by image editing operations are prevalent, but the color or illumination inconsistency between the manipulated region and background may make it unrealistic. Thus, it is important yet challenging to localize the…
Leveraging synthetically rendered data offers great potential to improve monocular depth estimation and other geometric estimation tasks, but closing the synthetic-real domain gap is a non-trivial and important task. While much recent work…
Over the last few years, deep learning based approaches have achieved outstanding improvements in natural image matting. Many of these methods can generate visually plausible alpha estimations, but typically yield blurry structures or…
Digital camera pipelines employ color constancy methods to estimate an unknown scene illuminant, in order to re-illuminate images as if they were acquired under an achromatic light source. Fully-supervised learning approaches exhibit…
This paper introduces a novel synthetic dataset that captures urban scenes under a variety of weather conditions, providing pixel-perfect, ground-truth-aligned images to facilitate effective feature alignment across domains. Additionally,…
In this paper, we study the problem of generating a set ofrealistic and diverse backgrounds when given only a smallforeground region. We refer to this task as image outpaint-ing. The technical challenge of this task is to synthesize notonly…
Image super-resolution is an important research area in computer vision that has a wide variety of applications including surveillance, medical imaging etc. Real-world signal image super-resolution has become very popular now-a-days due to…
In the field of image processing, applying intricate semantic modifications within existing images remains an enduring challenge. This paper introduces a pioneering framework that integrates viewpoint information to enhance the control of…
Ambient Lighting Normalization (ALN) aims to restore images degraded by complex, spatially varying illumination conditions. Existing methods, such as IFBlend, leverage frequency-domain priors to model illumination variations, but still…
One of the major challenges in the field of computer vision especially for detection, segmentation, recognition, monitoring, and automated solutions, is the quality of images. Image degradation, often caused by factors such as rain, fog,…
Image alignment and image restoration are classical computer vision tasks. However, there is still a lack of datasets that provide enough data to train and evaluate end-to-end deep learning models. Obtaining ground-truth data for image…
The purpose of training neural networks is to achieve high generalization performance on unseen inputs. However, when trained on imbalanced datasets, a model's prediction tends to favor majority classes over minority classes, leading to…
Histopathological images are essential for medical diagnosis and treatment planning, but interpreting them accurately using machine learning can be challenging due to variations in tissue preparation, staining and imaging protocols. Domain…