PulseAugur
实时 14:00:24
English(EN) LUCID: Learning Unified Control for Image Deflaring and Exposure Mastery in Nighttime Photography

新的LUCID框架统一了夜间照片修复

研究人员推出了一种新颖的LUCID框架,旨在通过同时解决图像眩光和曝光问题来增强夜间摄影效果。与以往分别处理这些问题的传统方法不同,LUCID将眩光解耦与扩散驱动的生成模型相结合。这种统一的方法实现了可控的修复,使用户能够通过四种训练模式来管理光源、伪影和动态范围。 AI

影响 引入了一种统一的图像修复方法,有望提高AI生成或增强的夜间照片的质量和可控性。

排序理由 该集群包含一篇详细介绍新图像处理方法的学术论文。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Tingyu Yang, Yuan Cheng, Xiaoyun Yuan ·

    LUCID:学习统一控制,实现夜间摄影图像去模糊和曝光精通

    arXiv:2606.06901v1 Announce Type: new Abstract: Photography is the art of painting with light, yet nighttime scenes are shaped by competing degradations: intense flares obscure scene structure, while photon-limited regions collapse into noise. Conventional approaches address thes…

  2. arXiv cs.CV TIER_1 English(EN) · Xiaoyun Yuan ·

    LUCID:学习统一控制,实现夜间摄影图像去模糊和曝光精通

    Photography is the art of painting with light, yet nighttime scenes are shaped by competing degradations: intense flares obscure scene structure, while photon-limited regions collapse into noise. Conventional approaches address these factors in isolation, overlooking the fact tha…