PPaperPicks

Jie Huang

University of Science and Technology of China, Hefei, China

22 papers at tracked venues · 20 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Token Painter: Training-Free Text-Guided Image Inpainting via Mask Autoregressive Models
  2. AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse
  3. Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution
  4. Decouple to Reconstruct: High Quality UHD Restoration Via Active Feature Disentanglement and Reversible Fusion
  5. FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining
  6. FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment
  7. FreePCA: Integrating Consistency Information across Long-short Frames in Training-free Long Video Generation via Principal Component Analysis
  8. Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement
  9. Navigating Image Restoration with VAR's Distribution Alignment Prior
  10. Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy
  11. UHD-processer: Unified UHD Image Restoration with Progressive Frequency Learning and Degradation-aware Prompts
  12. Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance
  13. FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining
  14. HomoFormer: Homogenized Transformer for Image Shadow Removal
  15. Image-free Pre-training for Low-Level Vision
  16. Learning Discriminative Noise Guidance for Image Forgery Detection and Localization
  17. Probing Synergistic High-Order Interaction in Infrared and Visible Image Fusion
  18. Revisiting Spatial-Frequency Information Integration from a Hierarchical Perspective for Panchromatic and Multi-Spectral Image Fusion
  19. Semantic Pre-supplement for Exposure Correction
  20. Training Pansharpening Networks at Full Resolution Using Degenerate Invariance
  21. Unleashing the Potential of the Semantic Latent Space in Diffusion Models for Image Dehazing
  22. Unmasking Bias in Diffusion Model Training