研究人员开发了ExpoCM，一个用于从单个低动态范围输入重建高动态范围（HDR）图像的新框架。该方法通过将问题重新表述为概率流ODE来解决过曝区域细节丢失和欠曝区域噪声的问题。ExpoCM使用曝光感知一致性轨迹和曝光引导损失函数，与现有的扩散模型相比，提高了图像质量并显著加快了推理时间。 AI
影响 为HDR图像重建提供了一种更快、更准确的方法，有望提高摄影和计算机视觉应用中的视觉质量。
排序理由 该集群包含一篇arXiv预印本，详细介绍了一种新的图像重建技术方法。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Single-image HDR reconstruction aims to recover high dynamic range radiance from a single low dynamic range (LDR) input, but remains highly ill-posed due to detail saturation in over-exposed regions and noise amplification in under-exposed areas. While recent diffusion-based appr…
arXiv:2605.02464v1 Announce Type: new Abstract: Single-image HDR reconstruction aims to recover high dynamic range radiance from a single low dynamic range (LDR) input, but remains highly ill-posed due to detail saturation in over-exposed regions and noise amplification in under-…
Single-image HDR reconstruction aims to recover high dynamic range radiance from a single low dynamic range (LDR) input, but remains highly ill-posed due to detail saturation in over-exposed regions and noise amplification in under-exposed areas. While recent diffusion-based appr…