Deep Tone Mapping Operator for High Dynamic Range Images

Abstract

A computationally fast tone mapping operator (TMO) that can quickly adapt to a wide spectrum of high dynamic range (HDR) content is quintessential for visualization on varied low dynamic range (LDR) output devices such as movie screens or standard displays. Existing TMOs can successfully tone-map only a limited number of HDR content and require an extensive parameter tuning to yield the best subjective-quality tone-mapped output. In this paper, we address this problem by proposing a fast, parameter-free and scene-adaptable deep tone mapping operator (DeepTMO) that yields a high-resolution and high-subjective quality tone mapped output. Based on conditional generative adversarial network (cGAN), DeepTMO not only learns to adapt to vast scenic-content (e.g., outdoor, indoor, human, structures, etc.) but also tackles the HDR related scene-specific challenges such as contrast and brightness, while preserving the fine-grained details. We explore 4 possible combinations of Generator-Discriminator architectural designs to specifically address some prominent issues in HDR related deep-learning frameworks like blurring, tiling patterns and saturation artifacts. By exploring different influences of scales, loss-functions and normalization layers under a cGAN setting, we conclude with adopting a multi-scale model for our task. To further leverage on the large-scale availability of unlabeled HDR data, we train our network by generating targets using an objective HDR quality metric, namely Tone Mapping Image Quality Index (TMQI). We demonstrate results both quantitatively and qualitatively, and showcase that our DeepTMO generates high-resolution, high-quality output images over a large spectrum of real-world scenes. Finally, we evaluate the perceived quality of our results by conducting a pair-wise subjective study which confirms the versatility of our method.

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Conditional Generative Adversarial Nets
• Deep Bilateral Learning for Real-Time Image Enhancement
• HDR image reconstruction from a single exposure using deep CNNs
• Deep Chain HDRI: Reconstructing a High Dynamic Range Image from a Single Low Dynamic Range Image
• Deep Feature Consistent Deep Image Transformations: Downscaling, Decolorization and HDR Tone Mapping
• Hybrid Loss for Learning Single-Image-based HDR Reconstruction
• Deep Inverse Tone Mapping Using LDR Based Learning for Estimating HDR Images with Absolute Luminance

Cited by in corpus (13)

• Learning to Adapt to Light
• Improved AI-generated Solar Farside Magnetograms by STEREO and SDO Data Sets and Their Release
• Distilling Style from Image Pairs for Global Forward and Inverse Tone Mapping
• Perceptual Tone Mapping Model for High Dynamic Range Imaging
• Joint tone mapping and denoising of thermal infrared images via multi-scale Retinex and multi-task learning
• AWNet: Attentive Wavelet Network for Image ISP
• Deep Learning for HDR Imaging: State-of-the-Art and Future Trends
• G-SemTMO: Tone Mapping with a Trainable Semantic Graph
• A review for Tone-mapping Operators on Wide Dynamic Range Image
• WDR FACE: The First Database for Studying Face Detection in Wide Dynamic Range
• Explorable Tone Mapping Operators
• Enhancing HDR Video Compression through CNN-based Effective Bit Depth Adaptation
• Unpaired Learning for High Dynamic Range Image Tone Mapping