PPaperPicks

Xiaopeng Zhang

National University of Singapore, Singapore

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

Venues

Frequent coauthors

Papers

  1. O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing
  2. CLIP-Adapted Region-to-Text Learning for Generative Open-Vocabulary Semantic Segmentation
  3. Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation
  4. IM-Zero: Instance-level Motion Controllable Video Generation in a Zero-shot Manner
  5. METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models
  6. SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation
  7. Segment Any 3D Gaussians
  8. Tackling View-Dependent Semantics in 3D Language Gaussian Splatting
  9. 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
  10. AlignZeg: Mitigating Objective Misalignment for Zero-Shot Semantic Segmentation
  11. BarLeRIa: An Efficient Tuning Framework for Referring Image Segmentation
  12. Bootstrap AutoEncoders With Contrastive Paradigm for Self-supervised Gaze Estimation
  13. Cascade-Zero123: One Image to Highly Consistent 3D with Self-prompted Nearby Views
  14. ControlVideo: Training-free Controllable Text-to-video Generation
  15. DomainFusion: Generalizing to Unseen Domains with Latent Diffusion Models
  16. GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models
  17. GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions
  18. Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners
  19. QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
  20. UMG-CLIP: A Unified Multi-granularity Vision Generalist for Open-World Understanding