no code implementations • 17 Apr 2024 • Navve Wasserman, Roman Beliy, Roy Urbach, Michal Irani
Combining Functional MRI (fMRI) data across different subjects and datasets is crucial for many neuroscience tasks.
1 code implementation • 1 Jun 2023 • Hila Chefer, Oran Lang, Mor Geva, Volodymyr Polosukhin, Assaf Shocher, Michal Irani, Inbar Mosseri, Lior Wolf
In this work, we present Conceptor, a novel method to interpret the internal representation of a textual concept by a diffusion model.
no code implementations • 5 May 2023 • Gon Buzaglo, Niv Haim, Gilad Yehudai, Gal Vardi, Michal Irani
Reconstructing samples from the training set of trained neural networks is a major privacy concern.
1 code implementation • ICCV 2023 • Roni Paiss, Ariel Ephrat, Omer Tov, Shiran Zada, Inbar Mosseri, Michal Irani, Tali Dekel
Our counting loss is deployed over automatically-created counterfactual examples, each consisting of an image and a caption containing an incorrect object count.
1 code implementation • 21 Nov 2022 • Yaniv Nikankin, Niv Haim, Michal Irani
Our image/video-specific diffusion model (SinFusion) learns the appearance and dynamics of the single image or video, while utilizing the conditioning capabilities of diffusion models.
no code implementations • CVPR 2023 • Bahjat Kawar, Shiran Zada, Oran Lang, Omer Tov, Huiwen Chang, Tali Dekel, Inbar Mosseri, Michal Irani
In this paper we demonstrate, for the very first time, the ability to apply complex (e. g., non-rigid) text-guided semantic edits to a single real image.
no code implementations • 24 Jul 2022 • Eyal Naor, Itai Antebi, Shai Bagon, Michal Irani
This allows to constrain the GS output video using video-specific constraints imposed by the RS input video.
1 code implementation • 15 Jun 2022 • Niv Haim, Gal Vardi, Gilad Yehudai, Ohad Shamir, Michal Irani
We propose a novel reconstruction scheme that stems from recent theoretical results about the implicit bias in training neural networks with gradient-based methods.
no code implementations • 7 Jun 2022 • Ganit Kupershmidt, Roman Beliy, Guy Gaziv, Michal Irani
Reconstructing natural videos from fMRI brain recordings is very challenging, for two main reasons: (i) As fMRI data acquisition is difficult, we only have a limited amount of supervised samples, which is not enough to cover the huge space of natural videos; and (ii) The temporal resolution of fMRI recordings is much lower than the frame rate of natural videos.
no code implementations • 11 May 2022 • Niv Haim, Ben Feinstein, Niv Granot, Assaf Shocher, Shai Bagon, Tali Dekel, Michal Irani
GANs are able to perform generation and manipulation tasks, trained on a single video.
2 code implementations • 24 Feb 2022 • Ron Mokady, Michal Yarom, Omer Tov, Oran Lang, Daniel Cohen-Or, Tali Dekel, Michal Irani, Inbar Mosseri
To meet these challenges, we proposed a StyleGAN-based self-distillation approach, which consists of two main components: (i) A generative-based self-filtering of the dataset to eliminate outlier images, in order to generate an adequate training set, and (ii) Perceptual clustering of the generated images to detect the inherent data modalities, which are then employed to improve StyleGAN's "truncation trick" in the image synthesis process.
1 code implementation • 16 Dec 2021 • Shiran Zada, Itay Benou, Michal Irani
In this paper, we present a surprisingly simple yet highly effective method to mitigate this limitation: using pure noise images as additional training data.
Ranked #1 on Long-tail Learning on CelebA-5
no code implementations • 17 Sep 2021 • Niv Haim, Ben Feinstein, Niv Granot, Assaf Shocher, Shai Bagon, Tali Dekel, Michal Irani
GANs are able to perform generation and manipulation tasks, trained on a single video.
1 code implementation • 9 Jun 2021 • Guy Gaziv, Michal Irani
This is applied to both: (i) the small number of images presented to subjects in an fMRI scanner (images for which we have fMRI recordings - referred to as "paired" data), and (ii) a very large number of natural images with no fMRI recordings ("unpaired data").
2 code implementations • ICCV 2021 • Oran Lang, Yossi Gandelsman, Michal Yarom, Yoav Wald, Gal Elidan, Avinatan Hassidim, William T. Freeman, Phillip Isola, Amir Globerson, Michal Irani, Inbar Mosseri
A natural source for such attributes is the StyleSpace of StyleGAN, which is known to generate semantically meaningful dimensions in the image.
2 code implementations • CVPR 2022 • Niv Granot, Ben Feinstein, Assaf Shocher, Shai Bagon, Michal Irani
Recently, however, Single Image GANs were introduced both as a superior solution for such manipulation tasks, but also for remarkable novel generative tasks.
1 code implementation • 19 Jun 2020 • Assaf Shocher, Ben Feinstein, Niv Haim, Michal Irani
We propose a generalization of the common Conv-layer, from a discrete layer to a Continuous Convolution (CC) Layer.
1 code implementation • CVPR 2020 • Sagie Benaim, Ariel Ephrat, Oran Lang, Inbar Mosseri, William T. Freeman, Michael Rubinstein, Michal Irani, Tali Dekel
We demonstrate how those learned features can boost the performance of self-supervised action recognition, and can be used for video retrieval.
1 code implementation • ECCV 2020 • Liad Pollak Zuckerman, Eyal Naor, George Pisha, Shai Bagon, Michal Irani
In particular, the higher spatial resolution of video frames provides strong examples as to how to increase the temporal resolution of that video.
2 code implementations • CVPR 2020 • Assaf Shocher, Yossi Gandelsman, Inbar Mosseri, Michal Yarom, Michal Irani, William T. Freeman, Tali Dekel
We demonstrate that our model results in a versatile and flexible framework that can be used in various classic and novel image generation tasks.
4 code implementations • NeurIPS 2019 • 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 (e. g. Bicubic downscaling).
Ranked #5 on Blind Super-Resolution on DIV2KRK - 2x upscaling
2 code implementations • NeurIPS 2019 • Roman Beliy, Guy Gaziv, Assaf Hoogi, Francesca Strappini, Tal Golan, Michal Irani
Unfortunately, acquiring sufficient "labeled" pairs of {Image, fMRI} (i. e., images with their corresponding fMRI responses) to span the huge space of natural images is prohibitive for many reasons.
no code implementations • 1 Feb 2019 • Yuval Bahat, Michal Irani, Gregory Shakhnarovich
Our approach is based on the observation that correctly classified images tend to exhibit robust and consistent classifications under certain image transformations (e. g., horizontal flip, small image translation, etc.).
1 code implementation • Computer Vision Foundation 2018 • Yossi Gandelsman, Assaf Shocher, Michal Irani
It was shown [Ulyanov et al] that the structure of a single DIP generator network is sufficient to capture the low-level statistics of a single image.
1 code implementation • 1 Dec 2018 • Assaf Shocher, Shai Bagon, Phillip Isola, Michal Irani
In this paper we propose an "Internal GAN" (InGAN) - an image-specific GAN - which trains on a single input image and learns its internal distribution of patches.
no code implementations • CVPR 2018 • Assaf Shocher, Nadav Cohen, Michal Irani
On such images, our method outperforms SotA CNN-based SR methods, as well as previous unsupervised SR methods.
7 code implementations • 17 Dec 2017 • Assaf Shocher, Nadav Cohen, Michal Irani
On such images, our method outperforms SotA CNN-based SR methods, as well as previous unsupervised SR methods.
Ranked #46 on Image Super-Resolution on BSD100 - 4x upscaling
no code implementations • ICCV 2017 • Yuval Bahat, Netalee Efrat, Michal Irani
It attempts to recover a sharp image which, on one hand - results in the blurry image under our estimated blur-field, and on the other hand - maximizes the internal recurrence of patches within and across scales of the recovered sharp image.
no code implementations • 14 Dec 2016 • Michal Yarom, Michal Irani
However, to find similar actions across videos, we consider only a small subset of the descriptors - the statistical significant descriptors.
no code implementations • CVPR 2016 • Or Lotan, Michal Irani
Reliable patch-matching forms the basis for many algorithms (super-resolution, denoising, inpainting, etc.)
no code implementations • CVPR 2013 • Maria Zontak, Inbar Mosseri, Michal Irani
While clean patches are obscured by severe noise in the original scale of a noisy image, noise levels drop dramatically at coarser image scales.