Deep HDR Hallucination for Inverse Tone Mapping

  title={Deep HDR Hallucination for Inverse Tone Mapping},
  author={Demetris Marnerides and Thomas Bashford-Rogers and Kurt Debattista},
  journal={Sensors (Basel, Switzerland)},
Inverse Tone Mapping (ITM) methods attempt to reconstruct High Dynamic Range (HDR) information from Low Dynamic Range (LDR) image content. The dynamic range of well-exposed areas must be expanded and any missing information due to over/under-exposure must be recovered (hallucinated). The majority of methods focus on the former and are relatively successful, while most attempts on the latter are not of sufficient quality, even ones based on Convolutional Neural Networks (CNNs). A major factor… Expand
Centered Multi-Task Generative Adversarial Network for Small Object Detection
This paper presents a centered multi-task generative adversarial network (CMTGAN), which combines small object detection and gaze estimation, and proposes a discriminator with detection loss for two-stageSmall object detection, which can be adapted to other GANs for object detection. Expand


Deep reverse tone mapping
The first deep-learning-based approach for fully automatic inference using convolutional neural networks is proposed, which can reproduce not only natural tones without introducing visible noise but also the colors of saturated pixels. Expand
A Two-stage Deep Network for High Dynamic Range Image Reconstruction
The qualitative and quantitative comparisons demonstrate that the proposed method can outperform the existing LDR to HDR works with a marginal difference and can reconstruct plausible HDR images without presenting any visual artefacts. Expand
ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content
This paper presents a method for generating HDR content from LDR content based on deep Convolutional Neural Networks (CNNs) termed ExpandNet, which accepts LDR images as input and generates images with an expanded range in an end‐to‐end fashion. Expand
Single image HDR reconstruction using a CNN with masked features and perceptual loss
This paper presents a novel learning-based approach to reconstruct an HDR image by recovering the saturated pixels of an input LDR image in a visually pleasing way, and proposes a feature masking mechanism that reduces the contribution of the features from the saturated areas. Expand
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
A new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs) is presented, which significantly outperforms existing methods, advancing both the quality and the resolution of deep image synthesis and editing. Expand
Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
This work model the HDR-to-LDR image formation pipeline as the dynamic range clipping, non-linear mapping from a camera response function, and quantization, and proposes to learn three specialized CNNs to reverse these steps. Expand
Evaluation of reverse tone mapping through varying exposure conditions
It is shown that current rTMO approaches fall short when the input image is not exposed properly, and proposed a method to automatically set a suitable gamma value for each image, based on the image key and empirical data, which enhances visible details without causing artifacts in incorrectly-exposed regions. Expand
Deep Chain HDRI: Reconstructing a High Dynamic Range Image from a Single Low Dynamic Range Image
A novel deep neural network model is proposed that reconstructs an HDR image from a single low dynamic range (LDR) image based on a convolutional neural network composed of dilated Convolutional layers and infers LDR images with various exposures and illumination from asingle LDR image of the same scene. Expand
Automatic high dynamic range hallucination in inverse tone mapping
An algorithm to compensate exposed regions of high dynamic range image hallucination for inverse tone mapping, which has the potential to be applied to video inverse tone-mapping with its automatic property. Expand
Large Scale GAN Training for High Fidelity Natural Image Synthesis
It is found that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick," allowing fine control over the trade-off between sample fidelity and variety by reducing the variance of the Generator's input. Expand