arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.09386cs.CV
收藏

一种用于高动态范围图像重建的两级深度网络

A Two-stage Deep Network for High Dynamic Range Image Reconstruction

Rigel-IT Bangladesh(Rigel-IT 孟加拉国);Sejong University(世宗大学);FS Solution

SMA Sharif, Rizwan Ali Naqvi, Mithun Biswas, Kim Sungjun

摘要:

将单次曝光的低动态范围(LDR)图像映射到高动态范围(HDR)被认为是最繁重的图像到图像转换任务之一,这是由于与曝光相关的丢失信息。这项研究通过提出一种新的两阶段深度网络来解决单次LDR到HDR映射的挑战。值得注意的是,我们提出的方法旨在重建HDR图像,而不知道硬件信息,包括相机响应函数(CRF)和曝光设置。因此,我们的目标是执行图像增强任务,如去噪,曝光校正等,在第一阶段。此外,我们的深度网络的第二阶段从数据样本的凸集学习色调映射和比特扩展。定性和定量的比较表明,该方法可以优于现有的LDR到HDR作品的边际差异。除此之外,我们还收集了一个包含不同相机系统的LDR图像数据集。与我们收集的真实世界的LDR图像的评估表明,所提出的方法可以重建合理的HDR图像,而不会出现任何视觉伪影。可用代码:https://github。com/sharif-apu/twostageHDR_NTIRE21。

英文摘要:

Mapping a single exposure low dynamic range (LDR) image into a high dynamic range (HDR) is considered among the most strenuous image to image translation tasks due to exposure-related missing information. This study tackles the challenges of single-shot LDR to HDR mapping by proposing a novel two-stage deep network. Notably, our proposed method aims to reconstruct an HDR image without knowing hardware information, including camera response function (CRF) and exposure settings. Therefore, we aim to perform image enhancement task like denoising, exposure correction, etc., in the first stage. Additionally, the second stage of our deep network learns tone mapping and bit-expansion from a convex set of data samples. The qualitative and quantitative comparisons demonstrate that the proposed method can outperform the existing LDR to HDR works with a marginal difference. Apart from that, we collected an LDR image dataset incorporating different camera systems. The evaluation with our collected real-world LDR images illustrates that the proposed method can reconstruct plausible HDR images without presenting any visual artefacts. Code available: https://github. com/sharif-apu/twostageHDR_NTIRE21.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑