Luoqi Liu

17

Papers

172

Total Citations

Papers (17)

Matching-CNN Meets KNN: Quasi-Parametric Human Parsing

SAM-REF: Introducing Image-Prompt Synergy during Interaction for Detail Enhancement in the Segment Anything Model

NTClick: Achieving Precise Interactive Segmentation With Noise-tolerant Clicks

GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing

Referring Image Segmentation via Cross-Modal Progressive Comprehension

DropKey for Vision Transformer

Towards Computational Baby Learning: A Weakly-Supervised Approach for Object Detection

Personalized Age Progression With Aging Dictionary

Recurrent 3D-2D Dual Learning for Large-Pose Facial Landmark Detection

Video Scene Parsing With Predictive Feature Learning

Locating Noise is Halfway Denoising for Semi-Supervised Segmentation

MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning

EVPGS: Enhanced View Prior Guidance for Splatting-based Extrapolated View Synthesis

MTADiffusion: Mask Text Alignment Diffusion Model for Object Inpainting

Memory Efficient Matting with Adaptive Token Routing

Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training

Towards Consistent Video Editing with Text-to-Image Diffusion Models