← 研踪 PaperTrailCVF · CVPR 2026:cvf:52cd68ded93bd21c1783517148bf9a43 · 记录 #1
RewardFlow: Generate Images by Optimizing What You Reward
Susladkar, OnkarJang, Dong-HwanPrakash, TusharJuvekar, AdheeshShah, VedantBarik, AyushBashir, NabeelWahed, MuntasirShrirao, RitishLourentzou, Ismini 来源日期(仅到年份) 2026
来源记录日期 2026
雷达观测 2026-11-01 23:43
摘要
RewardFlow is a zero-shot, training-free framework for text-guided image editing and generation based on reward-guided Langevin dynamics. We steer pretrained diffusion and flow-matching models at inference time using a diverse set of differentiable rewards, and control their influence with a prompt-aware adaptive policy that parses the text instruction, infers edit intent, and dynamically adjusts update steps. Our design includes a differentiable VQA-based reward for fine-grained semantic supervision and a SAM-guided reward for precise, localized edits with minimal leakage. Across standard image editing and compositional generation benchmarks, RewardFlow achieves state-of-the-art zero-shot edit fidelity and compositional alignment.
论文发现出处
这些页面提供论文线索,不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化,不是作者修订号。来源日期仅到月份或年份时,按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
RewardFlow: Generate Images by Optimizing What You Reward
RewardFlow is a zero-shot, training-free framework for text-guided image editing and generation based on reward-guided Langevin dynamics. We steer pretrained diffusion and flow-matching models at inference time using a diverse set of differentiable rewards, and control their influence with a prompt-aware adaptive policy that parses the text instruction, infers edit intent, and dynamically adjusts update steps. Our design includes a differentiable VQA-based reward for fine-grained semantic supervision and a SAM-guided reward for precise, localized edits with minimal leakage. Across standard image editing and compositional generation benchmarks, RewardFlow achieves state-of-the-art zero-shot edit fidelity and compositional alignment.
查看此版本解读 →查看此版本原文 ↗