Hong Gu

10

Papers

39

Total Citations

Papers (10)

SAFNet: Selective Alignment Fusion Network for Efficient HDR Imaging

VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers

FreeDiff: Progressive Frequency Truncation for Image Editing with Diffusion Models

CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models

RAP-SR: RestorAtion Prior Enhancement in Diffusion Models for Realistic Image Super-Resolution

OSDFace: One-Step Diffusion Model for Face Restoration

Textualize Visual Prompt for Image Editing via Diffusion Bridge

SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting

ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba

HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance