215 citations · 275 across the 16 of their papers we have counts for
20 papers
A Unified Theory of Image Scaling: Point Spread Functions, Discrete Kernels, and Scale-Spaces
Assaf Shocher
We derive the optically aligned system of image-scaling operators that reproduces optical zoom (exact zoom-out, canonical zoom-in), by identifying a Huygens-like con…
Moore, Escher, Penrose: A Conformal Golden Braid
Sophia Feldman, Assaf Shocher
I don't think I have ever done anything as peculiar in my life. Among other things, it shows a young man looking with interest at a print on the wall of an exhibition that features…
Pseudo-Invertible Neural Networks
Yamit Ehrlich, Nimrod Berman, Assaf Shocher
The Moore-Penrose Pseudo-inverse (PInv) serves as the fundamental solution for linear systems. In this paper, we propose a natural generalization of PInv to the nonlinear regime in…
Who Said Neural Networks Aren't Linear?
Nimrod Berman, Assaf Hallak, Assaf Shocher
Neural networks are famously nonlinear. However, linearity is defined relative to a pair of vector spaces, . Leveraging the algebraic concept of transport of structure,…
KernelFusion: Assumption-Free Blind Super-Resolution via Patch Diffusion
Oliver Heinimann, Assaf Shocher, Tal Zimbalist +1
Traditional super-resolution (SR) methods assume an ``ideal'' downscaling SR-kernel (e.g., bicubic downscaling) between the high-resolution (HR) image and the low-resolution (LR) i…
RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression
Uri Gadot, Assaf Shocher, Shie Mannor +2
Video encoders optimize compression for human perception by minimizing reconstruction error under bit-rate constraints. In many modern applications such as autonomous driving, an o…
IT: Idempotent Test-Time Training
Nikita Durasov, Assaf Shocher, Doruk Oner +3
Deep learning models often struggle when deployed in real-world settings due to distribution shifts between training and test data. While existing approaches like domain adaptation…
Idempotent Generative Network
Assaf Shocher, Amil Dravid, Yossi Gandelsman +3
We propose a new approach for generative modeling based on training a neural network to be idempotent. An idempotent operator is one that can be applied sequentially without changi…
Stochastic positional embeddings improve masked image modeling
Amir Bar, Florian Bordes, Assaf Shocher +6
Masked Image Modeling (MIM) is a promising self-supervised learning approach that enables learning from unlabeled images. Despite its recent success, learning good representations…
Rosetta Neurons: Mining the Common Units in a Model Zoo
Amil Dravid, Yossi Gandelsman, Alexei A. Efros +1
Do different neural networks, trained for various vision tasks, share some common representations? In this paper, we demonstrate the existence of common features we call "Rosetta N…
The Hidden Language of Diffusion Models
Hila Chefer, Oran Lang, Mor Geva +5
Text-to-image diffusion models have demonstrated an unparalleled ability to generate high-quality, diverse images from a textual prompt. However, the internal representations learn…
Diverse Video Generation from a Single Video
Niv Haim, Ben Feinstein, Niv Granot +4
GANs are able to perform generation and manipulation tasks, trained on a single video. However, these single video GANs require unreasonable amount of time to train on a single vid…
Diverse Generation from a Single Video Made Possible
Niv Haim, Ben Feinstein, Niv Granot +4
GANs are able to perform generation and manipulation tasks, trained on a single video. However, these single video GANs require unreasonable amount of time to train on a single vid…
Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models
Niv Granot, Ben Feinstein, Assaf Shocher +2
Single image generative models perform synthesis and manipulation tasks by capturing the distribution of patches within a single image. The classical (pre Deep Learning) prevailing…
From Discrete to Continuous Convolution Layers
Assaf Shocher, Ben Feinstein, Niv Haim +1
A basic operation in Convolutional Neural Networks (CNNs) is spatial resizing of feature maps. This is done either by strided convolution (donwscaling) or transposed convolution (u…
Semantic Pyramid for Image Generation
Assaf Shocher, Yossi Gandelsman, Inbar Mosseri +4
We present a novel GAN-based model that utilizes the space of deep features learned by a pre-trained classification model. Inspired by classical image pyramid representations, we c…
Blind Super-Resolution Kernel Estimation using an Internal-GAN
Sefi Bell-Kligler, Assaf Shocher, Michal Irani
Super resolution (SR) methods typically assume that the low-resolution (LR) image was downscaled from the unknown high-resolution (HR) image by a fixed 'ideal' downscaling kernel (…
"Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors
Yossi Gandelsman, Assaf Shocher, Michal Irani
Many seemingly unrelated computer vision tasks can be viewed as a special case of image decomposition into separate layers. For example, image segmentation (separation into foregro…
InGAN: Capturing and Remapping the "DNA" of a Natural Image
Assaf Shocher, Shai Bagon, Phillip Isola +1
Generative Adversarial Networks (GANs) typically learn a distribution of images in a large image dataset, and are then able to generate new images from this distribution. However,…
"Zero-Shot" Super-Resolution using Deep Internal Learning
Assaf Shocher, Nadav Cohen, Michal Irani
Deep Learning has led to a dramatic leap in Super-Resolution (SR) performance in the past few years. However, being supervised, these SR methods are restricted to specific training…