Qing Liu

21

Papers

166

Total Citations

Papers (21)

UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics

Generative Video Propagation

Generative Image Layer Decomposition with Visual Effects

FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction

UniHuman: A Unified Model For Editing Human Images in the Wild

ObjectMover: Generative Object Movement with Video Prior

CompleteMe: Reference-based Human Image Completion

Amodal Scene Analysis via Holistic Occlusion Relation Inference and Generative Mask Completion

SmartMask: Context Aware High-Fidelity Mask Generation for Fine-grained Object Insertion and Layout Control

Enhancing Facial Privacy Protection via Weakening Diffusion Purification

Compositional Convolutional Neural Networks: A Deep Architecture With Innate Robustness to Partial Occlusion

Weakly Supervised Instance Segmentation for Videos With Temporal Mask Consistency

Learning Part Segmentation Through Unsupervised Domain Adaptation From Synthetic Vehicles

SceneComposer: Any-Level Semantic Image Synthesis

Towards Open-World Segmentation of Parts

Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval

Semantic Part Detection via Matching: Learning to Generalize to Novel Viewpoints From Limited Training Data

Perceptual Artifacts Localization for Image Synthesis Tasks

Incremental Few-Shot Meta-Learning via Indirect Discriminant Alignment

PHOTOSWAP: Personalized Subject Swapping in Images