Dong Chen

13

Papers

65

Total Citations

Papers (13)

ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation

DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models

SmartEraser: Remove Anything from Images using Masked-Region Guidance

EPSD: Early Pruning with Self-Distillation for Efficient Model Compression

FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency

Wavelet and Prototype Augmented Query-based Transformer for Pixel-level Surface Defect Detection

Structured 3D Latents for Scalable and Versatile 3D Generation

AegisFL: Efficient and Flexible Privacy-Preserving Byzantine-Robust Cross-silo Federated Learning

FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts

Improved Noise Schedule for Diffusion Training

Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

Data Shunt: Collaboration of Small and Large Models for Lower Costs and Better Performance

InstructDiffusion: A Generalist Modeling Interface for Vision Tasks