arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2609.13135eess.IVcs.CVcs.GR

循环动态范围扩展

Recurrent Dynamic Range Extension

  • Simon Fraser University(西蒙弗雷泽大学)

机构由 AI 辅助整理,请以论文原文为准。

Sebastian Dille, Keru Fu, S. Mahdi H. Miangoleh, Yağız Aksoy

AI总结:

提出循环动态范围扩展方法,通过逐步增加曝光值并利用记忆回放训练,稳健重建长尾HDR场景,恢复明亮光源和高光。

AI中文摘要:

我们提出了一种逐步扩展图像高光区域的方法。我们不是直接重建复杂场景的完整动态范围,而是先学习一个更简单的任务:将输入图像的动态范围扩展一个曝光值。一旦掌握了这一点,我们通过循环执行我们的网络来检索场景的完整HDR图像,逐步增加输入的动态范围。我们的公式对输入动态范围不可知,并针对有界输出域。这使我们能够使用广泛可用的RAW图像进行重建任务,并调整对抗性损失以构建逼真的图像。通过结合记忆回放进行反向传播,我们可以在多个推理阶段循环训练我们的网络,并减少重建误差。因此,我们的系统能够稳健地重建具有挑战性的长尾HDR场景,并展示出对明亮光源和高光区域的强大恢复能力。

英文摘要:

We present an approach to progressively extend the highlights of an image. Instead of reconstructing the full dynamic range of a complex scene directly, we learn a simpler task first: We extend the dynamic range of an input image by a single exposure value. Once this is mastered, we retrieve the full HDR image for the scene by executing our network recurrently, progressively increasing the dynamic range of the input. Our formulation is agnostic to the input dynamic range and targets a bounded output domain. This enables us to use widely available RAW images for the reconstruction task and adapt adversarial losses to construct realistic images. By incorporating Memory Replay for backpropagation, we can train our network recurrently over multiple inference stages and reduce reconstruction errors. As a consequence, our system reconstructs challenging long-tailed HDR scenes robustly and shows powerful recovery of bright light sources and highlights.

补充信息

↑