activity
20192023
most citedAn Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

472 citations · 816 across the 27 of their papers we have counts for

collaborators
Showing 2021 · cs.CVShow all

8 papers · 2 filters

cs.CV2021

Leveraging in-domain supervision for unsupervised image-to-image translation tasks via multi-stream generators

Dvir Yerushalmi, Dov Danon, Amit H. Bermano

Supervision for image-to-image translation (I2I) tasks is hard to come by, but bears significant effect on the resulting quality. In this paper, we observe that for many Unsupervis…

cs.CV2021

Learned Queries for Efficient Local Attention

Moab Arar, Ariel Shamir, Amit H. Bermano

Vision Transformers (ViT) serve as powerful vision models. Unlike convolutional neural networks, which dominated vision research in previous years, vision transformers enjoy the ab…

cs.CV2021★ 2 cited

HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing

Yuval Alaluf, Omer Tov, Ron Mokady +2

The inversion of real images into StyleGAN's latent space is a well-studied problem. Nevertheless, applying existing approaches to real-world scenarios remains an open challenge, d…

cs.CV2021

StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators

Rinon Gal, Or Patashnik, Haggai Maron +2

Can a generative model be trained to produce images from a specific domain, guided by a text prompt only, without seeing any image? In other words: can an image generator be traine…

cs.CV2021★ 4 cited

JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting

Ron Mokady, Rotem Tzaban, Sagie Benaim +2

The task of unsupervised motion retargeting in videos has seen substantial advancements through the use of deep neural networks. While early works concentrated on specific object p…

cs.CV2021★ 4 cited

Pivotal Tuning for Latent-based Editing of Real Images

Daniel Roich, Ron Mokady, Amit H. Bermano +1

Recently, a surge of advanced facial editing techniques have been proposed that leverage the generative power of a pre-trained StyleGAN. To successfully edit an image this way, one…