Bridging Generative and Discriminative Models for Unified Visual Perception with Diffusion Priors

Documenti analoghi

• Foodfusion: A Novel Approach for Food Image Composition via Diffusion Models
  di: Shi, Chaohua, et al.
  Pubblicazione: (2024)
• Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution
  di: He, Xiao, et al.
  Pubblicazione: (2025)
• Disentangle Before Anonymize: A Two-stage Framework for Attribute-preserved and Occlusion-robust De-identification
  di: Zhu, Mingrui, et al.
  Pubblicazione: (2023)
• TeSG: Textual Semantic Guidance for Infrared and Visible Image Fusion
  di: Zhu, Mingrui, et al.
  Pubblicazione: (2025)
• Effective Diffusion Transformer Architecture for Image Super-Resolution
  di: Cheng, Kun, et al.
  Pubblicazione: (2024)