Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training

@inproceedings{Park2020MultiTemporalRN,
  title={Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training},
  author={Dongwon Park and Dong Un Kang and Jisoo Kim and Se Young Chun},
  booktitle={ECCV},
  year={2020}
}
Multi-scale (MS) approaches have been widely investigated for blind single image / video deblurring that sequentially recovers deblurred images in low spatial scale first and then in high spatial scale later with the output of lower scales. MS approaches have been effective especially for severe blurs induced by large motions in high spatial scale since those can be seen as small blurs in low spatial scale. In this work, we investigate alternative approach to MS, called multi-temporal (MT… 
View PDF on arXiv
View With Semantic Reader
39 Citations
Highly Influential Citations
5
Background Citations
17
Methods Citations
15
Results Citations
1

39 Citations

Citation Type

Citation Type

Blur More To Deblur Better: Multi-Blur2Deblur For Efficient Video Deblurring
TLDR
This work proposes multi-blur-to-deblur (MB2D), a novel concept to exploit neighboring frames for efficient video deblurring, inspired by unsharp masking, and argues that using more blurred images with long exposures as additional inputs significantly improves performance.
Blind Non-Uniform Motion Deblurring using Atrous Spatial Pyramid Deformable Convolution and Deblurring-Reblurring Consistency
TLDR
A new architecture which consists of multiple Atrous Spatial Pyramid Deformable Convolution (ASPDC) modules to deblur an image end-to-end with moreexibil-ity and a reblurring network to map the deblurred output back to the blurred input, which constrains the solution space is proposed.
Rethinking Coarse-to-Fine Approach in Single Image Deblurring
TLDR
This work revisits the coarse-to-fine strategy and presents a multi-input multi-output U-net (MIMO-UNet), which outperforms the state-of-the-art methods in terms of both accuracy and computational complexity.
Benchmarking Deep Deblurring Algorithms: A Large-Scale Multi-Cause Dataset and A New Baseline Model
TLDR
A new baseline model is proposed, level-attention deblurring network, to adapt to multiple causes of blurs and derives more powerful features with larger weights assigned to more important levels, thereby enhancing the feature representation.
Neural Maximum A Posteriori Estimation on Unpaired Data for Motion Deblurring
TLDR
A Neural Maximum A Posteriori (NeurMAP) estimation framework for training neural networks to recover blind motion information and sharp content from unpaired data and demonstrates superiority on both quantitative metrics and visual quality over state-of-the-art methods.
Non-uniform Motion Deblurring with Blurry Component Divided Guidance
Deep Residual Fourier Transformation for Single Image Deblurring
TLDR
A Residual Fast Fourier Transform with Convolution Block (Res FFT-Conv Block), capable of capturing both long-term and short-term interactions, while integrating both lowand high-frequency residual information, is presented.
SDWNet: A Straight Dilated Network with Wavelet Transformation for image Deblurring
TLDR
Qualitative and quantitative evaluations of real and synthetic datasets show that the deblurring method is comparable to existing algorithms in terms of performance with much lower training requirements.
Perceptual Variousness Motion Deblurring with Light Global Context Refinement
TLDR
This paper is the first to propose a light-weight globally-analyzing module into the image deblurring field, named Light Global Context Refinement (LGCR) module with exponentially lower cost, which achieves even better performance than the nonlocal unit.
SL-CycleGAN: Blind Motion Deblurring in Cycles using Sparse Learning
TLDR
This paper introduces an end-to-end generative adversarial network (GAN) based on sparse learning for single image blind motion deblurring, which is called SLCycleGAN and takes inspiration from the domain- to-domain translation ability of CycleGAN, and shows that imagedeblurring can be cycle-consistent while achieving the best qualitative results.
...
1
2
3
4
...

References

SHOWING 1-10 OF 55 REFERENCES
Deep Stacked Hierarchical Multi-Patch Network for Image Deblurring
TLDR
A deep {hierarchical multi-patch network} inspired by Spatial Pyramid Matching to deal with blurry images via a fine-to-coarse hierarchical representation and is the first real-time deep motion deblurring model for 720p images at 30fps.
Scale-Recurrent Network for Deep Image Deblurring
TLDR
A Scale-recurrent Network (SRN-DeblurNet) is proposed and shown to produce better quality results than state-of-the-arts, both quantitatively and qualitatively in single image deblurring.
Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
TLDR
This work proposes a multi-scale convolutional neural network that restores sharp images in an end-to-end manner where blur is caused by various sources and presents a new large-scale dataset that provides pairs of realistic blurry image and the corresponding ground truth sharp image that are obtained by a high-speed camera.
Recurrent Neural Networks With Intra-Frame Iterations for Video Deblurring
TLDR
This work aims to improve the accuracy of recurrent models by adapting the hidden states transferred from past frames to the frame being processed so that the relations between video frames could be better used.
Spatio-Temporal Filter Adaptive Network for Video Deblurring
TLDR
The proposed Spatio-Temporal Filter Adaptive Network (STFAN) takes both blurry and restored images of the previous frame as well as blurry image of the current frame as input, and dynamically generates the spatially adaptive filters for the alignment and deblurring.
Online Video Deblurring via Dynamic Temporal Blending Network
TLDR
An online (sequential) video deblurring method based on a spatio-temporal recurrent network that allows for realtime performance and introduces a novel architecture which extends the receptive field while keeping the overall size of the network small to enable fast execution.
Generalized video deblurring for dynamic scenes
TLDR
This work proposes a single energy model that simultaneously estimates optical flows and latent frames to solve the deblurring problem and achieves significant improvements in removing blurs and estimating accurate optical flows in blurry frames.
Non-uniform Blind Deblurring by Reblurring
TLDR
An approach for blind image deblurring, which handles non-uniform blurs, which exceeds the performance of state-of-the-art CNN-based blind-deblurring by a significant margin, without the need for any training data.
A Comparative Study for Single Image Blind Deblurring
TLDR
The first comprehensive perceptual study and analysis of single image blind deblurring using real-world blurred images and the correlation between human subjective scores and several full-reference and noreference image quality metrics is studied.
NTIRE 2019 Challenge on Video Deblurring and Super-Resolution: Dataset and Study
TLDR
It is found that the NTIRE 2019 challenges push the state-of-the-art in video deblurring and super-resolution, reaching compelling performance on the newly proposed REDS dataset.
...
1
2
3
4
5
...