High Dynamic Range Image Reconstruction from Saturated Images of Metallic Objects

• Published in: Journal of imaging Vol. 10; no. 4; p. 92
• Main Authors: Tominaga, Shoji, Horiuchi, Takahiko
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.04.2024
• Subjects: Algorithms; Analysis; Artificial neural networks; Cellular telephones; deep neural network approach; Digital cameras; Dynamic range; Evaluation; high dynamic range image reconstruction; Image databases; Image processing; Image reconstruction; Image resolution; Light; Lighting; Machine learning; material appearance; Metal products; metallic objects; Neural networks; Properties; reconstruction of saturated gloss; saturated low dynamic range images; Japan; saturated low dynamic range images; material appearance; reconstruction of saturated gloss; LDR-to-HDR mapping; high dynamic range image reconstruction; human psychological experiments; HDR image database; deep neural network approach; metallic objects; gloss perception
• ISSN: 2313-433X; 2313-433X
• DOI: 10.3390/jimaging10040092

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.