Zhe Lin

23

Papers

1,027

Total Citations

Papers (23)

InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning

Video-P2P: Video Editing with Cross-attention Control

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

ImageFolder: Autoregressive Image Generation with Folded Tokens

IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation

Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models

Generative Video Propagation

Generative Image Layer Decomposition with Visual Effects

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

Image Inpainting via Iteratively Decoupled Probabilistic Modeling

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

Removing Distributional Discrepancies in Captions Improves Image-Text Alignment

TurboFill: Adapting Few-step Text-to-image Model for Fast Image Inpainting

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers

TransPixeler: Advancing Text-to-Video Generation with Transparency

MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis

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

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

Multitwine: Multi-Object Compositing with Text and Layout Control

Brush2Prompt: Contextual Prompt Generator for Object Inpainting

DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization