Miaomiao Cui

16

Papers

96

Total Citations

Papers (16)

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

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

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

Towards Fine-grained Interactive Segmentation in Images and Videos

MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling

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

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

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

Boosting Semantic Human Matting With Coarse Annotations

PPR10K: A Large-Scale Portrait Photo Retouching Dataset With Human-Region Mask and Group-Level Consistency

ABPN: Adaptive Blend Pyramid Network for Real-Time Local Retouching of Ultra High-Resolution Photo

Unpaired Cartoon Image Synthesis via Gated Cycle Mapping

Structure-Aware Flow Generation for Human Body Reshaping

A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction From In-the-Wild Images

Box-Supervised Instance Segmentation with Level Set Evolution