Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter

Documenti analoghi

• Multi-modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation
  di: Li, Xiawei, et al.
  Pubblicazione: (2023)
• A Survey on Training-free Open-Vocabulary Semantic Segmentation
  di: Kombol, Naomi, et al.
  Pubblicazione: (2025)
• Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models
  di: Zhu, Xiaoyu, et al.
  Pubblicazione: (2024)
• ELBO-T2IAlign: A Generic ELBO-Based Method for Calibrating Pixel-level Text-Image Alignment in Diffusion Models
  di: Zhou, Qin, et al.
  Pubblicazione: (2025)
• Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation
  di: Shi, Yuheng, et al.
  Pubblicazione: (2024)