activity
20132023
most citedWorking Locally Thinking Globally: Theoretical Guarantees for Convolutional Sparse Coding

128 citations · 155 across the 10 of their papers we have counts for

collaborators
Showing 2023Show all

8 papers · 1 filter

hep-ex2023

Technical Design Report for the LUXE Experiment

H. Abramowicz, M. Almanza Soto, M. Altarelli +131

This Technical Design Report presents a detailed description of all aspects of the LUXE (Laser Und XFEL Experiment), an experiment that will combine the high-quality and high-energ…

cs.CV2023

CLIPAG: Towards Generator-Free Text-to-Image Generation

Roy Ganz, Michael Elad

Perceptually Aligned Gradients (PAG) refer to an intriguing property observed in robust image classification models, wherein their input gradients align with human perception and p…

cs.AI2023

Deep Optimal Transport: A Practical Algorithm for Photo-realistic Image Restoration

Theo Adrai, Guy Ohayon, Tomer Michaeli +1

We propose an image restoration algorithm that can control the perceptual quality and/or the mean square error (MSE) of any pre-trained model, trading one over the other at test ti…

cs.CV2023

Semi-supervised Quality Evaluation of Colonoscopy Procedures

Idan Kligvasser, George Leifman, Roman Goldenberg +2

Colonoscopy is the standard of care technique for detecting and removing polyps for the prevention of colorectal cancer. Nevertheless, gastroenterologists (GI) routinely miss appro…

cs.CV2023

Colonoscopy Coverage Revisited: Identifying Scanning Gaps in Real-Time

G. Leifman, I. Kligvasser, R. Goldenberg +2

Colonoscopy is the most widely used medical technique for preventing Colorectal Cancer, by detecting and removing polyps before they become malignant. Recent studies show that arou…

cs.CV2023

Nested Diffusion Processes for Anytime Image Generation

Noam Elata, Bahjat Kawar, Tomer Michaeli +1

Diffusion models are the current state-of-the-art in image generation, synthesizing high-quality images by breaking down the generation process into many fine-grained denoising ste…