Eli Shechtman

67

Papers

2,431

Total Citations

1

Affiliations

Affiliations

Adobe Research

Papers (67)

Toward Multimodal Image-to-Image Translation

NeurIPS 2017arXiv

One-step Diffusion with Distribution Matching Distillation

MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics

Lifespan Age Transformation Synthesis

From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

Long-Context State-Space Video World Models

Editable Image Elements for Controllable Synthesis

X-Fusion: Introducing New Modality to Frozen Large Language Models

Removing Distributional Discrepancies in Captions Improves Image-Text Alignment

Neural Face Editing With Intrinsic Image Disentangling

High-Resolution Image Inpainting Using Multi-Scale Neural Patch Synthesis

The Unreasonable Effectiveness of Deep Features as a Perceptual Metric

Multi-Content GAN for Few-Shot Font Style Transfer

ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing

Photometric Mesh Optimization for Video-Aligned 3D Object Reconstruction

Im2Pencil: Controllable Pencil Illustration From Photographs

Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture

Ensembling With Deep Generative Views

TransFill: Reference-Guided Image Inpainting by Merging Multiple Color and Spatial Transformations

StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation

Few-Shot Image Generation via Cross-Domain Correspondence

Spatially-Adaptive Pixelwise Networks for Fast Image Translation

RigNeRF: Fully Controllable Neural 3D Portraits

StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation

GAN-Supervised Dense Visual Alignment

Ensembling Off-the-Shelf Models for GAN Training

InsetGAN for Full-Body Image Generation

Automatic High Resolution Wire Segmentation and Removal

Semi-Supervised Parametric Real-World Image Harmonization

Domain Expansion of Image Generators

Scaling Up GANs for Text-to-Image Synthesis

SimpSON: Simplifying Photo Cleanup With Single-Click Distracting Object Segmentation Network

Realistic Saliency Guided Image Enhancement

Multi-Concept Customization of Text-to-Image Diffusion

PatchMatch-Based Automatic Lattice Detection for Near-Regular Textures

Learning a Discriminative Model for the Perception of Realism in Composite Images

Training Deep Networks to Be Spatially Sensitive

Localizing Moments in Video With Natural Language

Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation

Deep CG2Real: Synthetic-to-Real Translation via Image Disentanglement

UprightNet: Geometry-Aware Camera Orientation Estimation From Single Images

Modulated Periodic Activations for Generalizable Local Functional Representations

StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery

Collaging Class-Specific GANs for Semantic Image Synthesis

Ablating Concepts in Text-to-Image Diffusion Models

High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling

Look here! A parametric learning based approach to redirect visual attention

BlobGAN: Spatially Disentangled Scene Representations

Any-Resolution Training for High-Resolution Image Synthesis

Image Inpainting with Cascaded Modulation GAN and Object-Aware Training

Contrastive Learning for Diverse Disentangled Foreground Generation

Inpainting at Modern Camera Resolution by Guided PatchMatch with Auto-Curation

ChunkyGAN: Real Image Inversion via Segments

Controllable Shadow Generation Using Pixel Height Maps

Perceptual Artifacts Localization for Inpainting

ARF: Artistic Radiance Fields

Perceptual Artifacts Localization for Image Synthesis Tasks

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers

VideoGigaGAN: Towards Detail-rich Video Super-Resolution

SliderSpace: Decomposing the Visual Capabilities of Diffusion Models

Image Neural Field Diffusion Models

Brush2Prompt: Contextual Prompt Generator for Object Inpainting

Finding Distractors In Images

Controlling Perceptual Factors in Neural Style Transfer

Deep Photo Style Transfer

Swapping Autoencoder for Deep Image Manipulation

Few-shot Image Generation with Elastic Weight Consolidation