HDR-LFNet: Inverse tone mapping using fusion network

• Published in: Computers & graphics Vol. 114; pp. 1 - 12
• Main Authors: Chambe, Mathieu, Kijak, Ewa, Miklos, Zoltan, Le Meur, Olivier, Cozot, Rémi, Bouatouch, Kadi
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01-08-2023; Elsevier
• Subjects: Computational photography; Computer Science; High dynamic range imaging; Supervised machine learning; Computational photography; High dynamic range imaging; Supervised machine learning; machine learning; HDR imaging; iTMO
• ISSN: 0097-8493; 1873-7684
• DOI: 10.1016/j.cag.2023.05.007

To capture the real-world luminance values, High Dynamic Range (HDR) image processing has been developed. HDR images have a richer content than the widely-used Standard Dynamic Range (SDR) images, and are used in a number of situations, e.g. in film industry. As HDR displays are more and more commercially available, we need to be able to process HDR images as well as SDR ones (for example, devising denoising algorithms, inpainting or anti-aliasing). The most powerful methods to process images are now deep neural networks. However, the training of such networks calls for a lot of images, and HDR images datasets are relatively small.
One way to generate HDR images is inverse tone mapping operators (iTMOs). They are algorithms that expand the dynamic range of SDR images. In this paper, we propose HDR-LFNet, a novel iTMO, and its HDR training dataset. Our method merges several existing handcrafted iTMOs, combined in a supervised neural network to produce an HDR output. Our lightweight network requires less training images than state-of-the-art methods, and has faster training phase. Besides, the quality of the generated images is similar to the state-of-the-art. We present the architecture as well as the subjective and experimental evaluations of our method.
[Display omitted]
•We propose a new Inverse Tone Mapping Operator to create High Dynamic Range images.•Convolutional Neural Network are used to fuse together existing methods.•We performed a subjective study to evaluate our method.•The network’s weights and training set are available online.