Xiaobin Hu

12

Papers

68

Total Citations

Papers (12)

Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection

UniCombine: Unified Multi-Conditional Combination with Diffusion Transformer

DiffuMatting: Synthesizing Arbitrary Objects with Matting-level Annotation

VTON-HandFit: Virtual Try-on for Arbitrary Hand Pose Guided by Hand Priors Embedding

CustAny: Customizing Anything from A Single Example

GroundingFace: Fine-grained Face Understanding via Pixel Grounding Multimodal Large Language Model

MobileMamba: Lightweight Multi-Receptive Visual Mamba Network

OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic Typography

Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing

DVHGNN: Multi-Scale Dilated Vision HGNN for Efficient Vision Recognition

SVFR: A Unified Framework for Generalized Video Face Restoration

Sonic: Shifting Focus to Global Audio Perception in Portrait Animation