ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content

@article{Marnerides2018ExpandNetAD,
  title={ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content},
  author={Demetris Marnerides and Thomas Bashford-Rogers and Jonathan Hatchett and Kurt Debattista},
  journal={Computer Graphics Forum},
  year={2018},
  volume={37}
}
High dynamic range (HDR) imaging provides the capability of handling real world lighting as opposed to the traditional low dynamic range (LDR) which struggles to accurately represent images with higher dynamic range. [] Key Method The model attempts to reconstruct missing information that was lost from the original signal due to quantization, clipping, tone mapping or gamma correction.
Single image HDR synthesis using a Densely Connected Dilated ConvNet
  • A. AkhilK., C. Jiji
  • Computer Science
    2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2021
TLDR
A deep convolutional neural network model with a stack of dilated Convolutional blocks for reconstructing a HDR image from a single LDR image and results show that the model effectively captures missing information that was lost from the original image.
HDRNET: Single-Image-based HDR Reconstruction Using Channel Attention CNN
TLDR
An end-to-end convolutional neural network (CNN) termed HDRNET is presented to directly reconstruct HDR image given only a single 8-bit LDR image, which does not require any human expertise.
A Two-stage Deep Network for High Dynamic Range Image Reconstruction
TLDR
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.
FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network
TLDR
A dense feedback block is designed and an end-to-end feedback network-FHDR is proposed for HDR image generation from a single exposure LDR image, showing the superiority of this approach over the state-of-the-art methods.
HSVNet: Reconstructing HDR Image from a Single Exposure LDR Image with CNN
TLDR
The proposed method, HSVNet, is a deep learning architecture using a Convolutional Neural Networks (CNN) based U-net that uses the HSV color space that enables the network to identify saturated regions and adaptively focus on crucial components.
HDR-cGAN: single LDR to HDR image translation using conditional GAN
TLDR
A novel conditional GAN (cGAN) based framework trained in an end-to-end fashion over the HDR-REAL and HDR-SYNTH datasets is presented, which uses an overexposed mask obtained from a pre-trained segmentation model to facilitate the hallucination task of adding details in the saturated regions.
Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
TLDR
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.
Dual-Streams Global Guided Learning for High Dynamic Range Image Reconstruction
TLDR
A dual-streams global guided end-to-end learning method to reconstruct HDR image from a single LDR input that combines both global information and local image features.
Enhanced Tone Mapping Using Regional Fused GAN Training with a Gamma-Shift Dataset
TLDR
A GAN training optimization model for converting LDR images into HDR images that complements the performance of an object detection model even in a real night environment is proposed and outperforms conventional models in a comparison test.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 73 REFERENCES
Deep high dynamic range imaging of dynamic scenes
TLDR
A convolutional neural network is used as the learning model and three different system architectures are compared to model the HDR merge process to demonstrate the performance of the system by producing high-quality HDR images from a set of three LDR images.
HDR image reconstruction from a single exposure using deep CNNs
TLDR
This paper addresses the problem of predicting information that have been lost in saturated image areas, in order to enable HDR reconstruction from a single exposure, and proposes a deep convolutional neural network (CNN) that is specifically designed taking into account the challenges in predicting HDR values.
Deep reverse tone mapping
TLDR
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.
High Dynamic Range Imaging and Low Dynamic Range Expansion for Generating HDR Content
TLDR
The goal of this report is to provide a comprehensive overview on HDR Imaging, and an in depth review on these emerging topics.
Image Super-Resolution Using Deep Convolutional Networks
We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep
Deep Outdoor Illumination Estimation
TLDR
It is demonstrated that the approach allows the recovery of plausible illumination conditions and enables photorealistic virtual object insertion from a single image and significantly outperforms previous solutions to this problem.
Optimal exposure compression for high dynamic range content
TLDR
This work presents an alternative to tone mapping-based HDR content compression by identifying a single exposure that can reproduce the most information from the original HDR image that can be adapted to fit within the bit depth of any traditional encoder.
Deep Feature Consistent Deep Image Transformations: Downscaling, Decolorization and HDR Tone Mapping
TLDR
The Deep Feature Consistent Deep Image Transformation (DFC-DIT) framework is developed which unifies challenging one-to-many mapping image processing problems such as image downscaling, decolorization and high dynamic range (HDR) image tone mapping.
Learning High Dynamic Range from Outdoor Panoramas
TLDR
This work first captures lighting with a regular, LDR omnidirectional camera, and aims to recover the HDR after the fact via a novel, learning-based inverse tonemapping method which regresses linear, high dynamic range data from non-linear, saturated, low dynamic range panoramas.
Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification
TLDR
A novel technique to automatically colorize grayscale images that combines both global priors and local image features and can process images of any resolution, unlike most existing approaches based on CNN.
...
1
2
3
4
5
...