Revealing Latent Information: A Physics-inspired Self-supervised Pre-training Framework for Noisy and Sparse Events

Documenti analoghi

• Temporal Residual Guided Diffusion Framework for Event-Driven Video Reconstruction
  di: Zhu, Lin, et al.
  Pubblicazione: (2024)
• EMatch: A Unified Framework for Event-based Optical Flow and Stereo Matching
  di: Zhang, Pengjie, et al.
  Pubblicazione: (2024)
• Positive2Negative: Breaking the Information-Lossy Barrier in Self-Supervised Single Image Denoising
  di: Li, Tong, et al.
  Pubblicazione: (2024)
• Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train
  di: Wang, Zhao, et al.
  Pubblicazione: (2023)
• H-Flow: Self-supervised Human Scene Flow via Physics-inspired Joint Multi-modal Learning
  di: Huang, Zhanbo, et al.
  Pubblicazione: (2026)