Deep Chain HDRI: Reconstructing a High Dynamic Range Image from a Single Low Dynamic Range Image

Abstract

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.

10 pages

References in corpus (4)

• Conditional Generative Adversarial Nets
• HDR image reconstruction from a single exposure using deep CNNs
• Self-Normalizing Neural Networks
• Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network

Cited by in corpus (16)

• Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss
• Deep Tone Mapping Operator for High Dynamic Range Images
• Hybrid Loss for Learning Single-Image-based HDR Reconstruction
• Deep HDR Hallucination for Inverse Tone Mapping
• Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
• LHDR: HDR Reconstruction for Legacy Content using a Lightweight DNN
• High dynamic range image forensics using cnn
• HDR-cGAN: Single LDR to HDR Image Translation using Conditional GAN
• Deep Learning for HDR Imaging: State-of-the-Art and Future Trends
• High Dynamic Range Imaging via Visual Attention Modules
• Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramas
• Luminance Attentive Networks for HDR Image and Panorama Reconstruction
• Spectrally Consistent UNet for High Fidelity Image Transformations
• Optimal HDR and Depth from Dual Cameras
• Deep Snapshot HDR Imaging Using Multi-Exposure Color Filter Array
• Exposure Interpolation by Combining Model-driven and Data-driven Methods