Publications

Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models

Magnitude Attention-based Dynamic Pruning

CutMAA: Motion-Aware Data Augmentation for Light Field Super-Resolution

Imperceptible Protection Against Style Imitation from Diffusion Models

DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Models

Data Augmentation for Low-Level Vision: CutBlur and Mixture-of-Augmentation

Decomposing Texture and Semantics for Out-of-distribution Detection

DiffBlender: Scalable and Composable Multimodal Text-to-Image Diffusion Models

AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks

Interactive Cartoonization with Controllable Perceptual Factors

LPMM: Intuitive Pose Control for Neural Talking-Head Model via Landmark-Parameter Morphable Model

WebtoonMe: A Data-Centric Approach for Full-Body Portrait Stylization

Efficient Deep Neural Network for Photo-Realistic Image Super-Resolution

Cross-Domain Style Mixing for Face Cartoonization

Exploiting Distortion Information for Multi-Degraded Image Restoration

What is Wrong With One-Class Anomaly Detection?

Restoring Spatially-Heterogeneous Distortions Using Mixture of Experts Network

Rethinking Data Augmentation for Image Super-Resolution: A Comprehensive Analysis and a New Strategy

SimUSR: A Simple but Strong Baseline for Unsupervised Image Super-Resolution

Fast, Accurate, and Lightweight Super-Resolution With Cascading Residual Network

Image Super-Resolution via Progressive Cascading Residual Network

Image Distortion Detection Using Convolutional Neural Network