High Dynamic Range Image Reconstruction from Saturated Images of Metallic Objects

TL;DR

This paper presents a deep learning method to reconstruct high dynamic range images from single low dynamic range images of metallic objects.

Contribution

A novel CNN-based approach using a U-Net-like architecture for HDR image reconstruction from saturated LDR images of metallic objects.

Findings

The proposed CNN outperformed existing methods in reconstruction accuracy.

The method showed superior histogram fitting and psychological evaluation results.

The network achieved high resolution using an encoder-decoder structure with skip connections.

Abstract

This study considers a method for reconstructing a high dynamic range (HDR) original image from a single saturated low dynamic range (LDR) image of metallic objects. A deep neural network approach was adopted for the direct mapping of an 8-bit LDR image to HDR. An HDR image database was first constructed using a large number of various metallic objects with different shapes. Each captured HDR image was clipped to create a set of 8-bit LDR images. All pairs of HDR and LDR images were used to train and test the network. Subsequently, a convolutional neural network (CNN) was designed in the form of a deep U-Net-like architecture. The network consisted of an encoder, a decoder, and a skip connection to maintain high image resolution. The CNN algorithm was constructed using the learning functions in MATLAB. The entire network consisted of 32 layers and 85,900 learnable parameters. The performance of the proposed method was examined in experiments using a test image set. The proposed method was also compared with other methods and confirmed to be significantly superior in terms of reconstruction accuracy, histogram fitting, and psychological evaluation.

Figures