Search Results - "El Helou, Majed"

Fuzzy-Conditioned Diffusion and Diffusion Projection Attention Applied to Facial Image Correction by Helou, Majed El

“…Image diffusion has recently shown remarkable performance in image synthesis and implicitly as an image prior. Such a prior has been used with conditioning to…”
Get full text

PoGaIN: Poisson-Gaussian Image Noise Modeling From Paired Samples by Bahler, Nicolas, Helou, Majed El, Objois, Etienne, Okumus, Kaan, Susstrunk, Sabine

“…Image noise can often be accurately fitted to a Poisson-Gaussian distribution. However, estimating the distribution parameters from a noisy image only is a…”
Get full text

Blind Universal Bayesian Image Denoising With Gaussian Noise Level Learning by El Helou, Majed, Susstrunk, Sabine

“…Blind and universal image denoising consists of using a unique model that denoises images with any level of noise. It is especially practical as noise levels…”
Get full text

BIGPrior: Toward Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration by El Helou, Majed, Susstrunk, Sabine

“…Classic image-restoration algorithms use a variety of priors, either implicitly or explicitly. Their priors are hand-designed and their corresponding weights…”
Get full text

Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks by Lin, Xiaoyu, Bhattacharjee, Deblina, El Helou, Majed, Susstrunk, Sabine

“…Image classification has significantly improved using deep learning. This is mainly due to convolutional neural networks (CNNs) that are capable of learning…”
Get full text

PDA-RWSR: Pixel-Wise Degradation Adaptive Real-World Super-Resolution by Aakerberg, Andreas, El Helou, Majed, Nasrollahi, Kamal, Moeslund, Thomas

“…While many methods have been proposed to solve the Super-Resolution (SR) problem of Low-Resolution (LR) images with complex unknown degradations, their…”
Get full text

Deep Gaussian Denoiser Epistemic Uncertainty and Decoupled Dual-Attention Fusion by Ma, Xiaoqi, Lin, Xiaoyu, Helou, Majed El, Susstrunk, Sabine

“…Following the performance breakthrough of denoising networks, improvements have come chiefly through novel architecture designs and increased depth. While…”
Get full text

AAM: AN Assessment Metric of Axial Chromatic Aberration by Helou, Majed El, Dumbgen, Frederike, Siisstrunk, Sabine

“…Knowledge of lens characteristics is important to identify the best lens for a given capture scenario and application. Lens manufacturers provide many…”
Get full text

AL2: Progressive Activation Loss for Learning General Representations in Classification Neural Networks by Helou, Majed El, Dumbgen, Frederike, Susstrunk, Sabine

“…The large capacity of neural networks enables them to learn complex functions. To avoid overfitting, networks however require a lot of training data that can…”
Get full text

Correlation-based deblurring leveraging multispectral chromatic aberration in color and near-infrared joint acquisition by Helou, Majed El, Sadeghipoor, Zahra, Susstrunk, Sabine

“…Joint acquisition of color and near-infrared (NIR) images is of growing interest due to various applications that make use of the additional spectral…”
Get full text

PoGaIN: Poisson-Gaussian Image Noise Modeling from Paired Samples by Bähler, Nicolas, Helou, Majed El, Objois, Étienne, Okumuş, Kaan, Süsstrunk, Sabine

“…Image noise can often be accurately fitted to a Poisson-Gaussian distribution. However, estimating the distribution parameters from a noisy image only is a…”
Get full text

Mobile Robotic Painting of Texture by Helou, Majed El, Mandt, Stephan, Krause, Andreas, Beardsley, Paul

“…Robotic painting is well-established in controlled factory environments, but there is now potential for mobile robots to do functional painting tasks around…”
Get full text

Realizability of Planar Point Embeddings from Angle Measurements by Dümbgen, Frederike, Helou, Majed El, Scholefield, Adam

“…IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2020) Localization of a set of nodes is an important and a thoroughly…”
Get full text

Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning by Helou, Majed El, Süsstrunk, Sabine

“…IEEE Transactions on Image Processing, vol. 29, pp. 4885-4897, 2020 Blind and universal image denoising consists of using a unique model that denoises images…”
Get full text

Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks by Lin, Xiaoyu, Bhattacharjee, Deblina, Helou, Majed El, Süsstrunk, Sabine

“…IEEE Signal Processing Letters 28 (2021) 1719 - 1723 Image classification has significantly improved using deep learning. This is mainly due to convolutional…”
Get full text

Realizability of Planar Point Embeddings from Angle Measurements by Dumbgen, Frederike, El Helou, Majed, Scholefield, Adam

“…Localization of a set of nodes is an important and a thoroughly researched problem in robotics and sensor networks. This paper is concerned with the theory of…”
Get full text

Fuzzy-Conditioned Diffusion and Diffusion Projection Attention Applied to Facial Image Correction by Helou, Majed El

“…Image diffusion has recently shown remarkable performance in image synthesis and implicitly as an image prior. Such a prior has been used with conditioning to…”
Get full text

Divergence-Based Adaptive Extreme Video Completion by El Helou, Majed, Zhou, Ruofan, Schmutz, Frank, Guibert, Fabrice, Susstrunk, Sabine

“…Extreme image or video completion, where, for instance, we only retain 1% of pixels in random locations, allows for very cheap sampling in terms of the…”
Get full text

Which Information Matters? Dissecting Human-written Multi-document Summaries with Partial Information Decomposition by Mascarell, Laura, L'Homme, Yan, Helou, Majed El

“…Understanding the nature of high-quality summaries is crucial to further improve the performance of multi-document summarization. We propose an approach to…”
Get full text

BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration by Helou, Majed El, Süsstrunk, Sabine

“…Classic image-restoration algorithms use a variety of priors, either implicitly or explicitly. Their priors are hand-designed and their corresponding weights…”
Get full text