DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut

Documenti analoghi

• VidEdit: Zero-Shot and Spatially Aware Text-Driven Video Editing
  di: Couairon, Paul, et al.
  Pubblicazione: (2023)
• FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models
  di: Corradini, Barbara Toniella, et al.
  Pubblicazione: (2024)
• JAFAR: Jack up Any Feature at Any Resolution
  di: Couairon, Paul, et al.
  Pubblicazione: (2025)
• NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering
  di: Chambon, Loick, et al.
  Pubblicazione: (2025)
• Skipping Computations in Multimodal LLMs
  di: Shukor, Mustafa, et al.
  Pubblicazione: (2024)