Qingyi Tao

7

Papers

33

Total Citations

Papers (7)

Harmonizing Visual Representations for Unified Multimodal Understanding and Generation

SA-LUT: Spatial Adaptive 4D Look-Up Table for Photorealistic Style Transfer

MatAnyone: Stable Video Matting with Consistent Memory Propagation

Exploring Bottom-Up and Top-Down Cues With Attentive Learning for Webly Supervised Object Detection

Modeling Continuous Motion for 3D Point Cloud Object Tracking

Towards Robust and Expressive Whole-body Human Pose and Shape Estimation

PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance