Daniel Cohen-Or

44

Papers

295

Total Citations

Papers (44)

ReNoise: Real Image Inversion Through Iterative Noising

SAI3D: Segment Any Instance in 3D Scenes

Stable Flow: Vital Layers for Training-Free Image Editing

MAS: Multi-view Ancestral Sampling for 3D Motion Generation Using 2D Diffusion

EmoEdit: Evoking Emotions through Image Manipulation

Layered Image Vectorization via Semantic Simplification

Style Aligned Image Generation via Shared Attention

Breathing Life Into Sketches Using Text-to-Video Priors

Generating Non-Stationary Textures using Self-Rectification

Spherical Embedding of Inlier Silhouette Dissimilarities

PU-Net: Point Cloud Upsampling Network

Patch-Based Progressive 3D Point Set Upsampling

Blind Visual Motif Removal From a Single Image

ZigZagNet: Fusing Top-Down and Bottom-Up Context for Object Segmentation

PointGMM: A Neural GMM Network for Point Clouds

Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation

Single Pair Cross-Modality Super Resolution

Encoding in Style: A StyleGAN Encoder for Image-to-Image Translation

ShapeFormer: Transformer-Based Shape Completion via Sparse Representation

LARGE: Latent-Based Regression Through GAN Semantics

Domain Expansion of Image Generators

Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures

MoDi: Unconditional Motion Synthesis From Diverse Data

NULL-Text Inversion for Editing Real Images Using Guided Diffusion Models

Cascaded Feature Network for Semantic Segmentation of RGB-D Images

PU-GAN: A Point Cloud Upsampling Adversarial Network

CompoNet: Learning to Generate the Unseen by Part Synthesis and Composition

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

StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery

ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement

SKED: Sketch-guided Text-based 3D Editing

Delta Denoising Score

Localizing Object-Level Shape Variations with Text-to-Image Diffusion Models

CLIPascene: Scene Sketching with Different Types and Levels of Abstraction

Cross-Domain Cascaded Deep Translation

GANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation

Shape-Pose Disentanglement Using SE(3)-Equivariant Vector Neurons

MotionCLIP: Exposing Human Motion Generation to CLIP Space

FLEX: Extrinsic Parameters-Free Multi-View 3D Human Motion Reconstruction

Omni-ID: Holistic Identity Representation Designed for Generative Tasks

TriTex: Learning Texture from a Single Mesh via Triplane Semantic Features

NeuralSVG: An Implicit Representation for Text-to-Vector Generation

Dynamic Typography: Bringing Text to Life via Video Diffusion Prior

CLiC: Concept Learning in Context