Learning Blind Motion Deblurring

  title={Learning Blind Motion Deblurring},
  author={Patrick Wieschollek and Michael Hirsch and Bernhard Sch{\"o}lkopf and Hendrik P. A. Lensch},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
As handheld video cameras are now commonplace and available in every smartphone, images and videos can be recorded almost everywhere at anytime. However, taking a quick shot frequently yields a blurry result due to unwanted camera shake during recording or moving objects in the scene. Removing these artifacts from the blurry recordings is a highly ill-posed problem as neither the sharp image nor the motion blur kernel is known. Propagating information between multiple consecutive blurry… 

Figures and Tables from this paper

Densenet-Based Multi-scale Recurrent Network for Video Restoration with Gaussian Blur
This work proposes an efficient approach to produce a significant amount of realistic training data and introduces a novel multi-scale recurrent network architecture to deblur frames taking temporal information into account and demonstrates the effectiveness of the proposed method.
Video Deblurring via Temporally and Spatially Variant Recurrent Neural Network
Quantitative and qualitative evaluations on standard benchmark datasets demonstrate that the proposed method outperforms the current state-of-the-art methods for video deblurring.
Learning Event-Based Motion Deblurring
This paper starts from a sequential formulation of event-based motion deblurring, then shows how its optimization can be unfolded with a novel end-toend deep architecture, and proposes a differentiable directional event filtering module to effectively extract rich boundary prior from the evolution of events.
Burst Image Deblurring Using Permutation Invariant Convolutional Neural Networks
The novel convolutional architecture has a simultaneous view of all frames in the burst, and by construction treats them in an order-independent manner to effectively detect and leverage subtle cues scattered across different frames, while ensuring that each frame gets a full and equal consideration regardless of its position in the sequence.
Deep Video Deblurring Using Sharpness Features From Exemplars
This article develops an encoder and decoder network and explores the sharpness features from exemplars to guide the network for better image restoration, and demonstrates that the proposed algorithm performs favorably against state-of-the-art approaches on the benchmark video deblurring datasets and real-world images.
Reblur2Deblur: Deblurring videos via self-supervised learning
This work fine-tunes existing deblurring neural networks in a self-supervised fashion by enforcing that the output, when blurred based on the optical flow between subsequent frames, matches the input blurry image.
Learning to Extract a Video Sequence from a Single Motion-Blurred Image
This work presents a deep learning scheme that gradually reconstructs a temporal ordering by sequentially extracting pairs of frames and introduces loss functions invariant to the temporal order, which lets a neural network choose during training what frame to output among the possible combinations.


Deep Video Deblurring
This work introduces a deep learning solution to video deblurring, where a CNN is trained end-to-end to learn how to accumulate information across frames, and shows that the features learned extend todeblurring motion blur that arises due to camera shake in a wide range of videos.
Hand-Held Video Deblurring Via Efficient Fourier Aggregation
Experiments with numerous videos recorded in the wild, along with extensive comparisons, show that the proposed algorithm achieves state-of-the-art results while at the same time being much faster than its competitors.
Motion Deblurring in the Wild
A deep learning approach to remove motion blur from a single image captured in the wild, i.e., in an uncontrolled setting, is proposed and both a novel convolutional neural network architecture and a dataset for blurry images with ground truth are designed.
Intra-frame deblurring by leveraging inter-frame camera motion
The proposed video deblurring method effectively leverages the information distributed across multiple video frames due to camera motion, jointly estimating the motion between consecutive frames and blur within each frame.
CNN for license plate motion deblurring
This work explores the previously proposed approach of direct blind deconvolution and denoising with convolutional neural networks (CNN) in a situation where the blur kernels are partially constrained and evaluates the behavior and limits of the CNNs with respect to blur direction range and length.
Blind motion deblurring using multiple images
Burst deblurring: Removing camera shake through fourier burst accumulation
  • M. Delbracio, G. Sapiro
  • Computer Science
    2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
If the photographer takes a burst of images, a modality available in virtually all modern digital cameras, it is shown that it is possible to combine them to get a clean sharp version without explicitly solving any blur estimation and subsequent inverse problem.
Dynamic Scene Deblurring using a Locally Adaptive Linear Blur Model
A single energy model that jointly estimates optical flows, defocus blur maps and latent frames is proposed and it is demonstrated that the proposed method produces qualitatively superior performance than the state-of-the-art methods which often fail in either deblurring or optical flow estimation.
A Neural Approach to Blind Motion Deblurring
A new method for blind motion deblurring that uses a neural network trained to compute estimates of sharp image patches from observations that are blurred by an unknown motion kernel to predict the complex Fourier coefficients of a deconvolution filter to be applied to the input patch for restoration.
BlurBurst : Removing Blur Due to Camera Shake using Multiple Images
This paper demonstrates that an alternating sequence of convex programs can be used to recover both the latent image and blur kernels effectively and refers to this multi-image deblurring algorithm as BlurBurst.