Miaomiao Cui

9

Papers

110

Total Citations

Papers (9)

InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization

En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data

Perception-as-Control: Fine-grained Controllable Image Animation with 3D-aware Motion Representation

Towards Fine-grained Interactive Segmentation in Images and Videos

ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning

MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling

3DToonify: Creating Your High-Fidelity 3D Stylized Avatar Easily from 2D Portrait Images

DiffusionGAN3D: Boosting Text-guided 3D Generation and Domain Adaptation by Combining 3D GANs and Diffusion Priors

GaussianIP: Identity-Preserving Realistic 3D Human Generation via Human-Centric Diffusion Prior