Deep high dynamic range imaging of dynamic scenes

@article{Kalantari2017DeepHD,
  title={Deep high dynamic range imaging of dynamic scenes},
  author={Nima Khademi Kalantari and Ravi Ramamoorthi},
  journal={ACM Transactions on Graphics (TOG)},
  year={2017},
  volume={36},
  pages={1 - 12}
}
Producing a high dynamic range (HDR) image from a set of images with different exposures is a challenging process for dynamic scenes. A category of existing techniques first register the input images to a reference image and then merge the aligned images into an HDR image. However, the artifacts of the registration usually appear as ghosting and tearing in the final HDR images. In this paper, we propose a learning-based approach to address this problem for dynamic scenes. We use a convolutional… 
Multi-Scale Dense Networks for Deep High Dynamic Range Imaging
TLDR
A novel deep convolutional neural network is proposed to generate HDR, which attempts to produce more vivid images by using the coarse-to-fine scheme to gradually reconstruct the HDR image with the multi-scale architecture and residual network.
Deep HDR Reconstruction of Dynamic Scenes
TLDR
This paper puts forward an approach combining both traditional pipeline and deep learning algorithm, in which the input LDR images are aligned to the reference one using an optical flow method based on deep convolution network and then merged into HDR images using a powerful network which is called MergeNet.
CNN-Based Deghosting in High Dynamic Range Imaging
TLDR
A convolutional neural network (CNN)-based deghosting algorithm, which treats the estimation of motion maps as a labelling problem, which outperforms the state-of-the-art without requiring camera meta data and is more flexible to handle higher-resolution images under limited GPU memory compared to end-to-end networks for HDR imaging.
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.
Progressive and Selective Fusion Network for High Dynamic Range Imaging
TLDR
This paper proposes a novel method that can better fuse the features based on two ideas; one is multi-step feature fusion; the network gradually fuses the features in a stack of blocks having the same structure.
Attention-Mask Dense Merger (Attendense) Deep HDR for Ghost Removal
  • Kareem M. Metwaly, V. Monga
  • Computer Science
    ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2020
TLDR
A new deep HDR technique that does not need any explicit alignment of SDR images and a novel attention mask is developed that enables the network to focus on parts of the scene with considerable motion that leads to an economical network.
Single image HDR reconstruction using a CNN with masked features and perceptual loss
TLDR
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.
Single-Shot High Dynamic Range Imaging via Multiscale Convolutional Neural Network
TLDR
To effectively estimate the high-quality HDR images, a robust loss function is developed that considers the human visual system (HVS), color perception model, and multiscale contrast and can achieve synthesis results of significantly higher quality than conventional algorithms.
Deep Multi-Stage Learning for HDR With Large Object Motions
TLDR
This paper proposes to split the HDR problem into multiple stages and tackle them using separate Convolutional Neural Networks (CNNs) rather than attempting an end-to-end learning.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 63 REFERENCES
Reconstruction of high contrast images for dynamic scenes
TLDR
A novel bottom-up segmentation algorithm is developed through superpixel grouping which enables us to detect scene changes and directly generate the ghost-free LDR image of the dynamic scene.
Robust patch-based hdr reconstruction of dynamic scenes
TLDR
This paper proposes a new approach to HDR reconstruction that draws information from all the exposures but is more robust to camera/scene motion than previous techniques and presents results that show considerable improvement over previous approaches.
Hybrid Patching for a Sequence of Differently Exposed Images With Moving Objects
TLDR
This paper proposes a hybrid patching scheme composed of a correction method which is an intensity mapping function at pixel level, and a hole-filling method that uses block-level template matching that is able to prevent ghosting artifacts from appearing in the final synthesized HDR image.
Robust High Dynamic Range Imaging by Rank Minimization
TLDR
A rank minimization algorithm is presented which simultaneously aligns LDR images and detects outliers for robust HDR generation and is evaluated systematically and qualitatively with results from the state-of-the-art HDR algorithms using challenging real world examples.
Learning-based view synthesis for light field cameras
TLDR
This paper proposes a novel learning-based approach to synthesize new views from a sparse set of input views that could potentially decrease the required angular resolution of consumer light field cameras, which allows their spatial resolution to increase.
Convolutional Sparse Coding for High Dynamic Range Imaging
TLDR
It is demonstrated how to make CSC practical for HDR imaging by evaluating optical coding schemes, analyzing algorithmic parameters, and building a prototype coded HDR camera that demonstrates the utility of convolutional sparse HDRI coding with a custom hardware platform.
Artifact-free High Dynamic Range imaging
TLDR
This work presents a technique capable of dealing with a large amount of movement in the scene: it finds, in all the available exposures, patches consistent with a reference image previously selected from the stack and generates the HDR image by averaging the radiance estimates of all such regions.
Let there be color!
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.
Bitmap Movement Detection: HDR for Dynamic Scenes
TLDR
This work presents a method that adapts Exposure Fusion, as well as standard HDR techniques, to allow for dynamic scene without introducing artefacts, and shows that the proposed technique is able to deal with a large amount of movement in the scene and different movement configurations.
A versatile HDR video production system
TLDR
This work presents an optical architecture for HDR imaging that allows simultaneous capture of high, medium, and low-exposure images on three sensors at high fidelity with efficient use of the available light and presents an HDR merging algorithm to complement this architecture.
...
1
2
3
4
5
...