כתבה
arXiv cs.LG ·
Learned Adaptive Multiresolution Diffusion Imaging
אפליקציות של תיאור תמונה וסקירה של תמונות, עם שימוש במודלים של רכיבי רשת
תקציר מקורי באנגליתarXiv:2610.07884v1 Announce Type: cross Abstract: Adaptive multiresolution methods reduce representation cost by concentrating fine-scale degrees of freedom where needed, but their tree updates are usually governed by fixed local criteria. We introduce Learned Adaptive Multiresolution Diffusion Imaging (Learned AMDI), which preserves the AMDI fixed-tree propagator and hierarchy constraints while replacing the post-propagation selector with a shared local policy trained by proximal policy optimization. Regression tests reproduce deterministic AMDI trajectories to machine precision when identical trees are used. In the Haar implementation studied here, the deterministic one-step selector accepts no refinements in 54 decisions. Across nine held-out cases, Learned AMDI executes 393 refinements
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית