Search Results for author: Dani Lischinski

Found 41 papers, 19 papers with code

Cross-Domain Cascaded Deep Translation

no code implementations ECCV 2020 Oren Katzir, Dani Lischinski, Daniel Cohen-Or

We mitigate this by descending the deep layers of a pre-trained network, where the deep features contain more semantics, and applying the translation between these deep features.

Image-to-Image Translation Translation

EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes

no code implementations ICCV 2023 Jingyuan Yang, Qirui Huang, Tingting Ding, Dani Lischinski, Daniel Cohen-Or, Hui Huang

Most of the existing work in this area focuses on feature design, while little attention has been paid to dataset construction.

Emotion Recognition

SVNR: Spatially-variant Noise Removal with Denoising Diffusion

no code implementations28 Jun 2023 Naama Pearl, Yaron Brodsky, Dana Berman, Assaf Zomet, Alex Rav Acha, Daniel Cohen-Or, Dani Lischinski

Our formulation also accounts for the correlation that exists between the condition image and the samples along the modified diffusion process.

Image Denoising

Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields

1 code implementation22 Jun 2023 Ori Gordon, Omri Avrahami, Dani Lischinski

We present Blended-NeRF, a robust and flexible framework for editing a specific region of interest in an existing NeRF scene, based on text prompts, along with a 3D ROI box.

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

Data Roaming and Early Fusion for Composed Image Retrieval

no code implementations16 Mar 2023 Matan Levy, Rami Ben-Ari, Nir Darshan, Dani Lischinski

We study the task of Composed Image Retrieval (CoIR), where a query is composed of two modalities, image and text, extending the user's expression ability.

Composed Image Retrieval (CoIR) Retrieval

SpaText: Spatio-Textual Representation for Controllable Image Generation

no code implementations CVPR 2023 Omri Avrahami, Thomas Hayes, Oran Gafni, Sonal Gupta, Yaniv Taigman, Devi Parikh, Dani Lischinski, Ohad Fried, Xi Yin

Due to lack of large-scale datasets that have a detailed textual description for each region in the image, we choose to leverage the current large-scale text-to-image datasets and base our approach on a novel CLIP-based spatio-textual representation, and show its effectiveness on two state-of-the-art diffusion models: pixel-based and latent-based.

Blended Latent Diffusion

1 code implementation6 Jun 2022 Omri Avrahami, Ohad Fried, Dani Lischinski

Our solution leverages a recent text-to-image Latent Diffusion Model (LDM), which speeds up diffusion by operating in a lower-dimensional latent space.

Image Inpainting text-guided-image-editing +1

Shape-Pose Disentanglement using SE(3)-equivariant Vector Neurons

no code implementations3 Apr 2022 Oren Katzir, Dani Lischinski, Daniel Cohen-Or

We introduce an unsupervised technique for encoding point clouds into a canonical shape representation, by disentangling shape and pose.

Disentanglement Translation

Multi-level Latent Space Structuring for Generative Control

no code implementations11 Feb 2022 Oren Katzir, Vicky Perepelook, Dani Lischinski, Daniel Cohen-Or

Truncation is widely used in generative models for improving the quality of the generated samples, at the expense of reducing their diversity.

Third Time's the Charm? Image and Video Editing with StyleGAN3

1 code implementation31 Jan 2022 Yuval Alaluf, Or Patashnik, Zongze Wu, Asif Zamir, Eli Shechtman, Dani Lischinski, Daniel Cohen-Or

In particular, we demonstrate that while StyleGAN3 can be trained on unaligned data, one can still use aligned data for training, without hindering the ability to generate unaligned imagery.

Disentanglement Image Generation +1

ShapeFormer: Transformer-based Shape Completion via Sparse Representation

1 code implementation CVPR 2022 Xingguang Yan, Liqiang Lin, Niloy J. Mitra, Dani Lischinski, Daniel Cohen-Or, Hui Huang

We present ShapeFormer, a transformer-based network that produces a distribution of object completions, conditioned on incomplete, and possibly noisy, point clouds.

Classification-Regression for Chart Comprehension

1 code implementation29 Nov 2021 Matan Levy, Rami Ben-Ari, Dani Lischinski

Our model is particularly well suited for realistic questions with out-of-vocabulary answers that require regression.

Chart Question Answering Classification +3

ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation

1 code implementation ICCV 2021 Jinming Cao, Hanchao Leng, Dani Lischinski, Danny Cohen-Or, Changhe Tu, Yangyan Li

The reason is that the learnt weights for balancing the importance between the shape and base components in ShapeConv become constants in the inference phase, and thus can be fused into the following convolution, resulting in a network that is identical to one with vanilla convolutional layers.

Semantic Segmentation Thermal Image Segmentation

GAN Cocktail: mixing GANs without dataset access

1 code implementation7 Jun 2021 Omri Avrahami, Dani Lischinski, Ohad Fried

In the second stage, we merge the rooted models by averaging their weights and fine-tuning them for each specific domain, using only data generated by the original trained models.

Transfer Learning

StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery

5 code implementations ICCV 2021 Or Patashnik, Zongze Wu, Eli Shechtman, Daniel Cohen-Or, Dani Lischinski

Inspired by the ability of StyleGAN to generate highly realistic images in a variety of domains, much recent work has focused on understanding how to use the latent spaces of StyleGAN to manipulate generated and real images.

Image Manipulation

Evaluation and Comparison of Edge-Preserving Filters

no code implementations26 Dec 2020 Sarah Gingichashvili, Dani Lischinski

Edge-preserving filters play an essential role in some of the most basic tasks of computational photography, such as abstraction, tonemapping, detail enhancement and texture removal, to name a few.

StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation

5 code implementations CVPR 2021 Zongze Wu, Dani Lischinski, Eli Shechtman

Manipulation of visual attributes via these StyleSpace controls is shown to be better disentangled than via those proposed in previous works.

Image Generation

DO-Conv: Depthwise Over-parameterized Convolutional Layer

1 code implementation22 Jun 2020 Jinming Cao, Yangyan Li, Mingchao Sun, Ying Chen, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen, Changhe Tu

Moreover, in the inference phase, the depthwise convolution is folded into the conventional convolution, reducing the computation to be exactly equivalent to that of a convolutional layer without over-parameterization.

Image Classification

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.

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

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

Unsupervised multi-modal Styled Content Generation

no code implementations10 Jan 2020 Omry Sendik, Dani Lischinski, Daniel Cohen-Or

The emergence of deep generative models has recently enabled the automatic generation of massive amounts of graphical content, both in 2D and in 3D.

Illuminant Chromaticity Estimation from Interreflections

no code implementations13 Jun 2019 Eytan Lifshitz, Dani Lischinski

In this paper, we present a new, physically-based, approach for estimating illuminant chromaticity from interreflections of light between diffuse surfaces.

Color Constancy

Cross-Domain Cascaded Deep Feature Translation

no code implementations4 Jun 2019 Oren Katzir, Dani Lischinski, Daniel Cohen-Or

Our translation is performed in a cascaded, deep-to-shallow, fashion, along the deep feature hierarchy: we first translate between the deepest layers that encode the higher-level semantic content of the image, proceeding to translate the shallower layers, conditioned on the deeper ones.

Image-to-Image Translation Translation

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

CrossNet: Latent Cross-Consistency for Unpaired Image Translation

no code implementations14 Jan 2019 Omry Sendik, Dani Lischinski, Daniel Cohen-Or

Recent GAN-based architectures have been able to deliver impressive performance on the general task of image-to-image translation.

Image-to-Image Translation Translation

Multi-Scale Context Intertwining for Semantic Segmentation

no code implementations ECCV 2018 Di Lin, Yuanfeng Ji, Dani Lischinski, Daniel Cohen-Or, Hui Huang

Accurate semantic image segmentation requires the joint consideration of local appearance, semantic information, and global scene context.

Image Segmentation Semantic Segmentation

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.

Structure-aware Generative Network for 3D-Shape Modeling

1 code implementation12 Aug 2018 Zhijie Wu, Xiang Wang, Di Lin, Dani Lischinski, Daniel Cohen-Or, Hui Huang

The key idea is that during the analysis, the two branches exchange information between them, thereby learning the dependencies between structure and geometry and encoding two augmented features, which are then fused into a single latent code.


DiDA: Disentangled Synthesis for Domain Adaptation

no code implementations21 May 2018 Jinming Cao, Oren Katzir, Peng Jiang, Dani Lischinski, Danny Cohen-Or, Changhe Tu, Yangyan Li

The key idea is that by learning to separately extract both the common and the domain-specific features, one can synthesize more target domain data with supervision, thereby boosting the domain adaptation performance.

Disentanglement Unsupervised Domain Adaptation

Non-Stationary Texture Synthesis by Adversarial Expansion

1 code implementation11 May 2018 Yang Zhou, Zhen Zhu, Xiang Bai, Dani Lischinski, Daniel Cohen-Or, Hui Huang

We demonstrate that this conceptually simple approach is highly effective for capturing large-scale structures, as well as other non-stationary attributes of the input exemplar.

Texture Synthesis

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

Neuron-level Selective Context Aggregation for Scene Segmentation

no code implementations22 Nov 2017 Zhenhua Wang, Fanglin Gu, Dani Lischinski, Daniel Cohen-Or, Changhe Tu, Baoquan Chen

Contextual information provides important cues for disambiguating visually similar pixels in scene segmentation.

Scene Segmentation

Joint Bi-Layer Optimization for Single-Image Rain Streak Removal

no code implementations ICCV 2017 Lei Zhu, Chi-Wing Fu, Dani Lischinski, Pheng-Ann Heng

A third prior is defined on the rain-streak layer R, based on similarity of patches to the extracted rain patches.

Rain Removal

A Holistic Approach for Data-Driven Object Cutout

no code implementations18 Aug 2016 Huayong Xu, Yangyan Li, Wenzheng Chen, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen

We show that the resulting P-maps may be used to evaluate how likely a rectangle proposal is to contain an instance of the class, and further process good proposals to produce an accurate object cutout mask.

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