2018 · 27 citations · 11 references
ComputingComputer ScienceComputer VisionDigital ImagingMachine LearningDeep LearningGenerative ModelingHigh-dynamic-range ImagingImage SynthesisMedical ImagingTone MappingGenerative Adversarial NetworksHdr Tone MappingHigh Dynamic Range (Hdr) ImagingInverse Tone Mapping
Transferring a low-dynamic-range (LDR) image to a high-dynamic-range (HDR) image, which is the so-called inverse tone mapping (iTM), is an important imaging technique to improve visual effects of imaging devices. In this paper, we propose a novel deep learning-based iTM method, which learns an inverse tone mapping network with a generative adversarial regularizer. In the framework of alternating optimization, we learn a U-Net-based HDR image generator to transfer input LDR images to HDR ones, and a simple CNN-based discriminator to classify the real HDR images and the generated ones. Specifically, when learning the generator we consider the content-related loss and the generative adversarial regularizer jointly to improve the stability and the robustness of the generated HDR images. Using the learned generator as the proposed inverse tone mapping network, we achieve superior iTM results to the state-of-the-art methods consistently.
11
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Christian Ledig, Lucas Theis, Ferenc Huszár et al. · 2017 · 12.3K citations
Photographic tone reproduction for digital images
Erik Reinhard, Michael Stark, Peter Shirley et al. · ACM Transactions on Graphics · 2002 · 984 citations
Rafał Mantiuk, Kil Joong Kim, Allan G. Rempel et al. · 2011 · 474 citations
Yuki Endo, Yoshihiro Kanamori, Jun Mitani · ACM Transactions on Graphics · 2017 · 337 citations