Fan Tang

papers

797

total citations

papers (17)

Inversion-Based Style Transfer With Diffusion Models

CVPR 2023arXiv

404

citations

DAE-GAN: Dynamic Aspect-Aware GAN for Text-to-Image Synthesis

ICCV 2021arXiv

121

citations

Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization

CVPR 2021arXiv

citations

U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentation

CVPR 2024arXiv

citations

Multi-turn Consistent Image Editing

ICCV 2025arXiv

citations

Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration

CVPR 2025arXiv

citations

Adversarial Robust Memory-Based Continual Learner

ICCV 2025arXiv

citations

Z-Magic: Zero-shot Multiple Attributes Guided Image Creator

CVPR 2025arXiv

citations

Z*: Zero-shot Style Transfer via Attention Reweighting

CVPR 2024

citations

AMDANet: Attention-Driven Multi-Perspective Discrepancy Alignment for RGB-Infrared Image Fusion and Segmentation

ICCV 2025

citations

StyTr2: Image Style Transfer With Transformers

CVPR 2022

citations

Beyond Words: Augmenting Discriminative Richness via Diffusions in Unsupervised Prompt Learning

CVPR 2025arXiv

citations

Fan Tang

papers (17)

Inversion-Based Style Transfer With Diffusion Models

DAE-GAN: Dynamic Aspect-Aware GAN for Text-to-Image Synthesis

Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization

Adaptive Assignment for Geometry Aware Local Feature Matching

Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework

Progressive Open Space Expansion for Open-Set Model Attribution

SIOD: Single Instance Annotated per Category per Image for Object Detection

Music Style Transfer with Time-Varying Inversion of Diffusion Models

U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentation

Multi-turn Consistent Image Editing

Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration

Adversarial Robust Memory-Based Continual Learner

Z-Magic: Zero-shot Multiple Attributes Guided Image Creator

Z*: Zero-shot Style Transfer via Attention Reweighting

AMDANet: Attention-Driven Multi-Perspective Discrepancy Alignment for RGB-Infrared Image Fusion and Segmentation

StyTr2: Image Style Transfer With Transformers

Beyond Words: Augmenting Discriminative Richness via Diffusions in Unsupervised Prompt Learning

papers (17)

Inversion-Based Style Transfer With Diffusion Models

DAE-GAN: Dynamic Aspect-Aware GAN for Text-to-Image Synthesis

Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization

Adaptive Assignment for Geometry Aware Local Feature Matching

Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework

Progressive Open Space Expansion for Open-Set Model Attribution

SIOD: Single Instance Annotated per Category per Image for Object Detection

Music Style Transfer with Time-Varying Inversion of Diffusion Models

U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentation

Multi-turn Consistent Image Editing

Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration

Adversarial Robust Memory-Based Continual Learner

Z-Magic: Zero-shot Multiple Attributes Guided Image Creator

Z*: Zero-shot Style Transfer via Attention Reweighting

AMDANet: Attention-Driven Multi-Perspective Discrepancy Alignment for RGB-Infrared Image Fusion and Segmentation

StyTr2: Image Style Transfer With Transformers

Beyond Words: Augmenting Discriminative Richness via Diffusions in Unsupervised Prompt Learning