Search Results for author: Kfir Aberman

Found 33 papers, 14 papers with code

Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation

no code implementations25 Mar 2024 Omer Dahary, Or Patashnik, Kfir Aberman, Daniel Cohen-Or

Text-to-image diffusion models have an unprecedented ability to generate diverse and high-quality images.

Denoising Text-to-Image Generation

MyVLM: Personalizing VLMs for User-Specific Queries

no code implementations21 Mar 2024 Yuval Alaluf, Elad Richardson, Sergey Tulyakov, Kfir Aberman, Daniel Cohen-Or

To effectively recognize a variety of user-specific concepts, we augment the VLM with external concept heads that function as toggles for the model, enabling the VLM to identify the presence of specific target concepts in a given image.

Image Captioning Language Modelling +2

E$^{2}$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation

no code implementations11 Jan 2024 Yifan Gong, Zheng Zhan, Qing Jin, Yanyu Li, Yerlan Idelbayev, Xian Liu, Andrey Zharkov, Kfir Aberman, Sergey Tulyakov, Yanzhi Wang, Jian Ren

One highly promising direction for enabling flexible real-time on-device image editing is utilizing data distillation by leveraging large-scale text-to-image diffusion models, such as Stable Diffusion, to generate paired datasets used for training generative adversarial networks (GANs).

Image-to-Image Translation

Personalized Restoration via Dual-Pivot Tuning

no code implementations28 Dec 2023 Pradyumna Chari, Sizhuo Ma, Daniil Ostashev, Achuta Kadambi, Gurunandan Krishnan, Jian Wang, Kfir Aberman

This approach ensures that personalization does not interfere with the restoration process, resulting in a natural appearance with high fidelity to the person's identity and the attributes of the degraded image.

Image Restoration

Orthogonal Adaptation for Modular Customization of Diffusion Models

no code implementations5 Dec 2023 Ryan Po, Guandao Yang, Kfir Aberman, Gordon Wetzstein

In this paper, we address a new problem called Modular Customization, with the goal of efficiently merging customized models that were fine-tuned independently for individual concepts.

3D Paintbrush: Local Stylization of 3D Shapes with Cascaded Score Distillation

1 code implementation16 Nov 2023 Dale Decatur, Itai Lang, Kfir Aberman, Rana Hanocka

In this work we develop 3D Paintbrush, a technique for automatically texturing local semantic regions on meshes via text descriptions.

State of the Art on Diffusion Models for Visual Computing

no code implementations11 Oct 2023 Ryan Po, Wang Yifan, Vladislav Golyanik, Kfir Aberman, Jonathan T. Barron, Amit H. Bermano, Eric Ryan Chan, Tali Dekel, Aleksander Holynski, Angjoo Kanazawa, C. Karen Liu, Lingjie Liu, Ben Mildenhall, Matthias Nießner, Björn Ommer, Christian Theobalt, Peter Wonka, Gordon Wetzstein

The field of visual computing is rapidly advancing due to the emergence of generative artificial intelligence (AI), which unlocks unprecedented capabilities for the generation, editing, and reconstruction of images, videos, and 3D scenes.

RealFill: Reference-Driven Generation for Authentic Image Completion

no code implementations28 Sep 2023 Luming Tang, Nataniel Ruiz, Qinghao Chu, Yuanzhen Li, Aleksander Holynski, David E. Jacobs, Bharath Hariharan, Yael Pritch, Neal Wadhwa, Kfir Aberman, Michael Rubinstein

Once personalized, RealFill is able to complete a target image with visually compelling contents that are faithful to the original scene.

TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis

no code implementations27 Jul 2023 Zihan Zhang, Richard Liu, Kfir Aberman, Rana Hanocka

The gradual nature of a diffusion process that synthesizes samples in small increments constitutes a key ingredient of Denoising Diffusion Probabilistic Models (DDPM), which have presented unprecedented quality in image synthesis and been recently explored in the motion domain.

Denoising Image Generation +1

HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models

2 code implementations13 Jul 2023 Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Wei Wei, Tingbo Hou, Yael Pritch, Neal Wadhwa, Michael Rubinstein, Kfir Aberman

By composing these weights into the diffusion model, coupled with fast finetuning, HyperDreamBooth can generate a person's face in various contexts and styles, with high subject details while also preserving the model's crucial knowledge of diverse styles and semantic modifications.

Diffusion Personalization Tuning Free

Break-A-Scene: Extracting Multiple Concepts from a Single Image

1 code implementation25 May 2023 Omri Avrahami, Kfir Aberman, Ohad Fried, Daniel Cohen-Or, Dani Lischinski

Text-to-image model personalization aims to introduce a user-provided concept to the model, allowing its synthesis in diverse contexts.

Complex Scene Breaking and Synthesis

Delta Denoising Score

no code implementations ICCV 2023 Amir Hertz, Kfir Aberman, Daniel Cohen-Or

We introduce Delta Denoising Score (DDS), a novel scoring function for text-based image editing that guides minimal modifications of an input image towards the content described in a target prompt.

Denoising Image-to-Image Translation +2

P+: Extended Textual Conditioning in Text-to-Image Generation

no code implementations16 Mar 2023 Andrey Voynov, Qinghao Chu, Daniel Cohen-Or, Kfir Aberman

Furthermore, we utilize the unique properties of this space to achieve previously unattainable results in object-style mixing using text-to-image models.

Denoising Text-to-Image Generation

Sketch-Guided Text-to-Image Diffusion Models

no code implementations24 Nov 2022 Andrey Voynov, Kfir Aberman, Daniel Cohen-Or

In this work, we introduce a universal approach to guide a pretrained text-to-image diffusion model, with a spatial map from another domain (e. g., sketch) during inference time.

Denoising Sketch-to-Image Translation

Null-text Inversion for Editing Real Images using Guided Diffusion Models

4 code implementations CVPR 2023 Ron Mokady, Amir Hertz, Kfir Aberman, Yael Pritch, Daniel Cohen-Or

Our Null-text inversion, based on the publicly available Stable Diffusion model, is extensively evaluated on a variety of images and prompt editing, showing high-fidelity editing of real images.

Image Generation Text-based Image Editing

DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation

10 code implementations CVPR 2023 Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Yael Pritch, Michael Rubinstein, Kfir Aberman

Once the subject is embedded in the output domain of the model, the unique identifier can be used to synthesize novel photorealistic images of the subject contextualized in different scenes.

Diffusion Personalization Image Generation

Prompt-to-Prompt Image Editing with Cross Attention Control

7 code implementations2 Aug 2022 Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, Daniel Cohen-Or

Editing is challenging for these generative models, since an innate property of an editing technique is to preserve most of the original image, while in the text-based models, even a small modification of the text prompt often leads to a completely different outcome.

Image Generation Text-based Image Editing

MoDi: Unconditional Motion Synthesis from Diverse Data

1 code implementation CVPR 2023 Sigal Raab, Inbal Leibovitch, Peizhuo Li, Kfir Aberman, Olga Sorkine-Hornung, Daniel Cohen-Or

In this work, we present MoDi -- a generative model trained in an unsupervised setting from an extremely diverse, unstructured and unlabeled dataset.

Motion Interpolation Motion Synthesis

GANimator: Neural Motion Synthesis from a Single Sequence

1 code implementation5 May 2022 Peizhuo Li, Kfir Aberman, Zihan Zhang, Rana Hanocka, Olga Sorkine-Hornung

We present GANimator, a generative model that learns to synthesize novel motions from a single, short motion sequence.

Motion Synthesis Style Transfer

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

Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure

no code implementations23 Nov 2021 Andreas Aristidou, Anastasios Yiannakidis, Kfir Aberman, Daniel Cohen-Or, Ariel Shamir, Yiorgos Chrysanthou

In this work, we present a music-driven motion synthesis framework that generates long-term sequences of human motions which are synchronized with the input beats, and jointly form a global structure that respects a specific dance genre.

Motion Synthesis

Deep Saliency Prior for Reducing Visual Distraction

no code implementations CVPR 2022 Kfir Aberman, Junfeng He, Yossi Gandelsman, Inbar Mosseri, David E. Jacobs, Kai Kohlhoff, Yael Pritch, Michael Rubinstein

Using only a model that was trained to predict where people look at images, and no additional training data, we can produce a range of powerful editing effects for reducing distraction in images.

Learning Skeletal Articulations with Neural Blend Shapes

1 code implementation6 May 2021 Peizhuo Li, Kfir Aberman, Rana Hanocka, Libin Liu, Olga Sorkine-Hornung, Baoquan Chen

Furthermore, we propose neural blend shapes--a set of corrective pose-dependent shapes which improve the deformation quality in the joint regions in order to address the notorious artifacts resulting from standard rigging and skinning.

Zoom-to-Inpaint: Image Inpainting with High-Frequency Details

1 code implementation17 Dec 2020 Soo Ye Kim, Kfir Aberman, Nori Kanazawa, Rahul Garg, Neal Wadhwa, Huiwen Chang, Nikhil Karnad, Munchurl Kim, Orly Liba

Although deep learning has enabled a huge leap forward in image inpainting, current methods are often unable to synthesize realistic high-frequency details.

Image Inpainting Super-Resolution +1

Neural Alignment for Face De-pixelization

no code implementations29 Sep 2020 Maayan Shuvi, Noa Fish, Kfir Aberman, Ariel Shamir, Daniel Cohen-Or

Although simple, our framework synthesizes high-quality face reconstructions, demonstrating that given the statistical prior of a human face, multiple aligned pixelated frames contain sufficient information to reconstruct a high-quality approximation of the original signal.

MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency

no code implementations22 Jun 2020 Mingyi Shi, Kfir Aberman, Andreas Aristidou, Taku Komura, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen

We introduce MotioNet, a deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video. While previous methods rely on either rigging or inverse kinematics (IK) to associate a consistent skeleton with temporally coherent joint rotations, our method is the first data-driven approach that directly outputs a kinematic skeleton, which is a complete, commonly used, motion representation.

Skeleton-Aware Networks for Deep Motion Retargeting

1 code implementation12 May 2020 Kfir Aberman, Peizhuo Li, Dani Lischinski, Olga Sorkine-Hornung, Daniel Cohen-Or, Baoquan Chen

In other words, our operators form the building blocks of a new deep motion processing framework that embeds the motion into a common latent space, shared by a collection of homeomorphic skeletons.

motion retargeting Motion Synthesis

Unpaired Motion Style Transfer from Video to Animation

1 code implementation12 May 2020 Kfir Aberman, Yijia Weng, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen

In this paper, we present a novel data-driven framework for motion style transfer, which learns from an unpaired collection of motions with style labels, and enables transferring motion styles not observed during training.

3D Reconstruction Motion Style Transfer +1

Learning Character-Agnostic Motion for Motion Retargeting in 2D

2 code implementations5 May 2019 Kfir Aberman, Rundi Wu, Dani Lischinski, Baoquan Chen, Daniel Cohen-Or

In order to achieve our goal, we learn to extract, directly from a video, a high-level latent motion representation, which is invariant to the skeleton geometry and the camera view.

3D Reconstruction motion retargeting +2

Deep Video-Based Performance Cloning

no code implementations21 Aug 2018 Kfir Aberman, Mingyi Shi, Jing Liao, Dani Lischinski, Baoquan Chen, Daniel Cohen-Or

After training a deep generative network using a reference video capturing the appearance and dynamics of a target actor, we are able to generate videos where this actor reenacts other performances.

Neural Best-Buddies: Sparse Cross-Domain Correspondence

2 code implementations10 May 2018 Kfir Aberman, Jing Liao, Mingyi Shi, Dani Lischinski, Baoquan Chen, Daniel Cohen-Or

Correspondence between images is a fundamental problem in computer vision, with a variety of graphics applications.

Image Morphing

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