发帖
雷达卡
摘要翻译：
本文提出了一种新的深度神经网络模型，该模型可以从单一的低动态范围(LDR)图像重建高动态范围(HDR)图像。该模型基于由膨胀卷积层组成的卷积神经网络，从同一场景的单个LDR图像中推断出不同曝光和光照下的LDR图像。然后，将这些推断结果合并就可以形成最终的HDR图像。由于该方法采用链式结构来推断给定LDR图像中具有较亮（或较暗）曝光的LDR图像之间的关系，因此相对容易找到LDR和具有不同比特深度的HDR之间的映射。该方法不仅扩展了范围，而且具有还原实际物理世界光信息的优点。对于该方法所获得的HDR图像，HDR-VDP2的Q值为56.36，与传统算法相比提高了6分，这是HDR图像最常用的评价指标，对于分辨率为1920×1200的显示器，该Q值为56.36分。另外，在比较该算法与传统算法产生的色调映射HDR图像的峰值信噪比时，该算法得到的平均值为30.86dB，比传统算法得到的峰值信噪比提高了10 dB。
---
英文标题：
《Deep Chain HDRI: Reconstructing a High Dynamic Range Image from a Single
Low Dynamic Range Image》
---
作者：
Siyeong Lee, Gwon Hwan An, Suk-Ju Kang
---
最新提交年份：
2018
---
分类信息：
一级分类：Computer Science 计算机科学
二级分类：Computer Vision and Pattern Recognition 计算机视觉与模式识别
分类描述：Covers image processing, computer vision, pattern recognition, and scene understanding. Roughly includes material in ACM Subject Classes I.2.10, I.4, and I.5.
涵盖图像处理、计算机视觉、模式识别和场景理解。大致包括ACM课程I.2.10、I.4和I.5中的材料。
--
一级分类：Electrical Engineering and Systems Science 电气工程与系统科学
二级分类：Image and Video Processing 图像和视频处理
分类描述：Theory, algorithms, and architectures for the formation, capture, processing, communication, analysis, and display of images, video, and multidimensional signals in a wide variety of applications. Topics of interest include: mathematical, statistical, and perceptual image and video modeling and representation; linear and nonlinear filtering, de-blurring, enhancement, restoration, and reconstruction from degraded, low-resolution or tomographic data; lossless and lossy compression and coding; segmentation, alignment, and recognition; image rendering, visualization, and printing; computational imaging, including ultrasound, tomographic and magnetic resonance imaging; and image and video analysis, synthesis, storage, search and retrieval.
用于图像、视频和多维信号的形成、捕获、处理、通信、分析和显示的理论、算法和体系结构。感兴趣的主题包括：数学，统计，和感知图像和视频建模和表示；线性和非线性滤波、去模糊、增强、恢复和重建退化、低分辨率或层析数据；无损和有损压缩编码；分割、对齐和识别；图像渲染、可视化和打印；计算成像，包括超声、断层和磁共振成像；以及图像和视频的分析、合成、存储、搜索和检索。
--
---
英文摘要：
In this paper, we propose a novel deep neural network model that reconstructs a high dynamic range (HDR) image from a single low dynamic range (LDR) image. The proposed model is based on a convolutional neural network composed of dilated convolutional layers, and infers LDR images with various exposures and illumination from a single LDR image of the same scene. Then, the final HDR image can be formed by merging these inference results. It is relatively easy for the proposed method to find the mapping between the LDR and an HDR with a different bit depth because of the chaining structure inferring the relationship between the LDR images with brighter (or darker) exposures from a given LDR image. The method not only extends the range, but also has the advantage of restoring the light information of the actual physical world. For the HDR images obtained by the proposed method, the HDR-VDP2 Q score, which is the most popular evaluation metric for HDR images, was 56.36 for a display with a 1920$\times$1200 resolution, which is an improvement of 6 compared with the scores of conventional algorithms. In addition, when comparing the peak signal-to-noise ratio values for tone mapped HDR images generated by the proposed and conventional algorithms, the average value obtained by the proposed algorithm is 30.86 dB, which is 10 dB higher than those obtained by the conventional algorithms.
---
PDF链接：
https://arxiv.org/pdf/1801.06277
京公网安备 11010802022788号
