Search Results for author: Yotam Nitzan

Found 10 papers, 6 papers with code

Lazy Diffusion Transformer for Interactive Image Editing

no code implementations18 Apr 2024 Yotam Nitzan, Zongze Wu, Richard Zhang, Eli Shechtman, Daniel Cohen-Or, Taesung Park, Michaël Gharbi

We demonstrate that our approach is competitive with state-of-the-art inpainting methods in terms of quality and fidelity while providing a 10x speedup for typical user interactions, where the editing mask represents 10% of the image.

Facial Reenactment Through a Personalized Generator

no code implementations12 Jul 2023 Ariel Elazary, Yotam Nitzan, Daniel Cohen-Or

In this paper, we propose a novel method for facial reenactment using a personalized generator.


MyStyle: A Personalized Generative Prior

no code implementations31 Mar 2022 Yotam Nitzan, Kfir Aberman, Qiurui He, Orly Liba, Michal Yarom, Yossi Gandelsman, Inbar Mosseri, Yael Pritch, Daniel Cohen-Or

Given a small reference set of portrait images of a person (~100), we tune the weights of a pretrained StyleGAN face generator to form a local, low-dimensional, personalized manifold in the latent space.

Image Enhancement Super-Resolution

State-of-the-Art in the Architecture, Methods and Applications of StyleGAN

no code implementations28 Feb 2022 Amit H. Bermano, Rinon Gal, Yuval Alaluf, Ron Mokady, Yotam Nitzan, Omer Tov, Or Patashnik, Daniel Cohen-Or

Of these, StyleGAN offers a fascinating case study, owing to its remarkable visual quality and an ability to support a large array of downstream tasks.

Image Generation

LARGE: Latent-Based Regression through GAN Semantics

1 code implementation CVPR 2022 Yotam Nitzan, Rinon Gal, Ofir Brenner, Daniel Cohen-Or

For modern generative frameworks, this semantic encoding manifests as smooth, linear directions which affect image attributes in a disentangled manner.

Attribute regression

Designing an Encoder for StyleGAN Image Manipulation

8 code implementations4 Feb 2021 Omer Tov, Yuval Alaluf, Yotam Nitzan, Or Patashnik, Daniel Cohen-Or

We then suggest two principles for designing encoders in a manner that allows one to control the proximity of the inversions to regions that StyleGAN was originally trained on.

Image Manipulation

Face Identity Disentanglement via Latent Space Mapping

3 code implementations15 May 2020 Yotam Nitzan, Amit Bermano, Yangyan Li, Daniel Cohen-Or

Learning disentangled representations of data is a fundamental problem in artificial intelligence.

De-identification Disentanglement

Cannot find the paper you are looking for? You can Submit a new open access paper.