Scott Cohen

papers

502

total citations

papers (19)

IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation

CVPR 2024arXiv

citations

Deepstrip: High-Resolution Boundary Refinement

CVPR 2020arXiv

citations

TopNet: Transformer-Based Object Placement Network for Image Compositing

CVPR 2023arXiv

citations

FineMatch: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction

ECCV 2024arXiv

citations

FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication

CVPR 2024arXiv

citations

GamutMLP: A Lightweight MLP for Color Loss Recovery

CVPR 2023arXiv

citations

GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing

ECCV 2022arXiv

citations

Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment

ICLR 2025arXiv

citations

MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis

CVPR 2025arXiv

citations

CompleteMe: Reference-based Human Image Completion

ICCV 2025arXiv

citations

The Photographer's Eye: Teaching Multimodal Large Language Models to See, and Critique Like Photographers

CVPR 2025

citations

Polarized Color Screen Matting

CVPR 2025

citations

Improving Closed and Open-Vocabulary Attribute Prediction Using Transformers

ECCV 2022

citations

ObjectStitch: Object Compositing With Diffusion Model

CVPR 2023

citations

AESOP: Abstract Encoding of Stories, Objects, and Pictures

ICCV 2021

citations

PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click

ECCV 2020

citations

Scott Cohen

papers (19)

PhraseCut: Language-Based Image Segmentation in the Wild

Learning To Predict Visual Attributes in the Wild

Image Inpainting with Cascaded Modulation GAN and Object-Aware Training

IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation

Deepstrip: High-Resolution Boundary Refinement

TopNet: Transformer-Based Object Placement Network for Image Compositing

FineMatch: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction

FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication

GamutMLP: A Lightweight MLP for Color Loss Recovery

GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing

Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment

MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis

CompleteMe: Reference-based Human Image Completion

The Photographer's Eye: Teaching Multimodal Large Language Models to See, and Critique Like Photographers

Polarized Color Screen Matting

Improving Closed and Open-Vocabulary Attribute Prediction Using Transformers

ObjectStitch: Object Compositing With Diffusion Model

AESOP: Abstract Encoding of Stories, Objects, and Pictures

PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click

papers (19)

PhraseCut: Language-Based Image Segmentation in the Wild

Learning To Predict Visual Attributes in the Wild

Image Inpainting with Cascaded Modulation GAN and Object-Aware Training

IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation

Deepstrip: High-Resolution Boundary Refinement

TopNet: Transformer-Based Object Placement Network for Image Compositing

FineMatch: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction

FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication

GamutMLP: A Lightweight MLP for Color Loss Recovery

GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing

Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment

MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis

CompleteMe: Reference-based Human Image Completion

The Photographer's Eye: Teaching Multimodal Large Language Models to See, and Critique Like Photographers

Polarized Color Screen Matting

Improving Closed and Open-Vocabulary Attribute Prediction Using Transformers

ObjectStitch: Object Compositing With Diffusion Model

AESOP: Abstract Encoding of Stories, Objects, and Pictures

PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click