Skip to main content
Search

# PIE-Bench

1 related articles

Subscribe to updates
  1. arXiv

    Treating Refinement Itself as the Editing Interface: How RefineEdit Edits Images Without Training in a Generative Refinement Network

    The work introduces RefineEdit, a training-free prompt-to-prompt image editing framework that couples edit localization with content generation inside the global refinement of binary image codes in a Generative Refinement Network (GRN): it branches an editing branch from an intermediate source state, uses the signed differences in the two branches' probabilities for the same source-sampled bits to select editable positions and bits, copies the evolving source state at all remaining bits, and stabilizes decisions across steps with adaptive spatial freezing and finite bit locking, achieving the best background-preservation scores (PSNR, LPIPS, MSE, SSIM) and the highest whole-image and edited-region CLIP scores among the evaluated methods across nine editing categories of PIE-Bench.

You’re all caught up