PPaperPicks

Jinwei Chen

Vivo Mobile Communication Co., Ltd., Shanghai, China

19 papers at tracked venues · 16 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Bidirectional Noise Injection: Enhancing Diffusion Models via Coordinated Input-Output Perturbation
  2. Advancing Comprehensive Aesthetic Insight with Multi-Scale Text-Guided Self-Supervised Learning
  3. AuthFace: Towards Authentic Blind Face Restoration with Face-oriented Generative Diffusion Prior
  4. Boosting Vision State Space Model with Fractal Scanning
  5. High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity
  6. Learning Adaptive Lighting via Channel-Aware Guidance
  7. MIPI 2025 Challenge on Deblurring for Hybrid EVS Camera: Methods and Results
  8. Multi-Task Dense Predictions via Unleashing the Power of Diffusion
  9. Photography Perspective Composition: Towards Aesthetic Perspective Recommendation
  10. SDMATTE: Grafting Diffusion Models for Interactive Matting
  11. SE-GUI: Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning
  12. Beta-Tuned Timestep Diffusion Model
  13. Chain of Visual Perception: Harnessing Multimodal Large Language Models for Zero-shot Camouflaged Object Detection
  14. Improving Adversarial Energy-Based Model via Diffusion Process
  15. Mono-ViFI: A Unified Learning Framework for Self-supervised Single and Multi-frame Monocular Depth Estimation
  16. Multi-Task Dense Prediction via Mixture of Low-Rank Experts
  17. Non-uniform Timestep Sampling: Towards Faster Diffusion Model Training
  18. Revisiting Single Image Reflection Removal in the Wild
  19. SAFNet: Selective Alignment Fusion Network for Efficient HDR Imaging