Blind Image Deblurring Using Dark Channel Prior

Pan, Jinshan; Sun, Deqing; Pfister, Hanspeter; Yang, Ming–Hsuan

doi:10.1109/cvpr.2016.180

Cited by 644 publications

(728 citation statements)

References 25 publications

Supporting

Mentioning

719

Contrasting

Unclassified

Order By: Relevance

“…We fit a Bradley-Terry model [3] to estimate the subjective score for each method so that they can be ranked, with the identical routine following the previous benchmark work [24,26]. Each blurry image is processed with each of the following algorithms: Krishnan et al [20], Whyte et al [49], Xu et al [51], Sun et al [43], Pan et al [36], DeepDeblur [33], SRN [45], DeblurGAN [21]; and the three DeblurGAN-v2 variants (Inception-ResNet-v2, Mo-bileNet, MobileNet-DSC). The eleven deblurring results, together with the original blurry image, are sent for pairwise comparison to construct the winning matrix.…”

Section: Subjective Evaluation On Lai Datasetmentioning

confidence: 99%

DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better

Kupyn

Martyniuk

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

706

622

View full text Add to dashboard Cite

We present a new end-to-end generative adversarial network (GAN) for single image motion deblurring, named DeblurGAN-v2, which considerably boosts state-of-the-art deblurring efficiency, quality, and flexibility. DeblurGAN-v2 is based on a relativistic conditional GAN with a doublescale discriminator. For the first time, we introduce the Feature Pyramid Network into deblurring, as a core building block in the generator of DeblurGAN-v2. It can flexibly work with a wide range of backbones, to navigate the balance between performance and efficiency. The plugin of sophisticated backbones (e.g., Inception-ResNet-v2) can lead to solid state-of-the-art deblurring. Meanwhile, with light-weight backbones (e.g., MobileNet and its variants), DeblurGAN-v2 reaches 10-100 times faster than the nearest competitors, while maintaining close to state-ofthe-art results, implying the option of real-time video deblurring. We demonstrate that DeblurGAN-v2 obtains very competitive performance on several popular benchmarks, in terms of deblurring quality (both objective and subjective), as well as efficiency. Besides, we show the architecture to be effective for general image restoration tasks too. Our codes, models and data are available at: https: //github.com/KupynOrest/DeblurGANv2.

show abstract

Section: Subjective Evaluation On Lai Datasetmentioning

confidence: 99%

DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better

Kupyn

Martyniuk

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

706

622

View full text Add to dashboard Cite

show abstract

“…A series of widely-used priors and regularizers are based on image gradient sparsity, such as the total variational regularizer [24], the Gaussian scale mixture prior [25], the l 1 \l 2 norm based prior [15], and the l 0 -norm regularize [14], [26]. Non-gradient-based priors have also been proposed, such as the edge-based patch prior [27], the colour line based prior [28], and the dark/white channel prior [29], [30]. Hu et al [13] proposed to jointly estimate the depth layering and remove non-uniform blur caused by the in-plane motion from a single blurred image.…”

Section: A Single View Deblurmentioning

confidence: 99%

Joint Stereo Video Deblurring, Scene Flow Estimation and Moving Object Segmentation

Pan

Dai

Liu

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Stereo videos for the dynamic scenes often show unpleasant blurred effects due to the camera motion and the multiple moving objects with large depth variations. Given consecutive blurred stereo video frames, we aim to recover the latent clean images, estimate the 3D scene flow and segment the multiple moving objects. These three tasks have been previously addressed separately, which fail to exploit the internal connections among these tasks and cannot achieve optimality. In this paper, we propose to jointly solve these three tasks in a unified framework by exploiting their intrinsic connections. To this end, we represent the dynamic scenes with the piece-wise planar model, which exploits the local structure of the scene and expresses various dynamic scenes. Under our model, these three tasks are naturally connected and expressed as the parameter estimation of 3D scene structure and camera motion (structure and motion for the dynamic scenes). By exploiting the blur model constraint, the moving objects and the 3D scene structure, we reach an energy minimization formulation for joint deblurring, scene flow and segmentation. We evaluate our approach extensively on both synthetic datasets and publicly available real datasets with fastmoving objects, camera motion, uncontrolled lighting conditions and shadows. Experimental results demonstrate that our method can achieve significant improvement in stereo video deblurring, scene flow estimation and moving object segmentation, over stateof-the-art methods.

show abstract

“…Recently, with the fast progress of regularization and optimization theory, many sophisticated image priors [3]- [12] were proposed to handle the single image blind image deblurring problem with general blur kernels, such as the mixture of Gaussians prior that fits the heavy-tailed prior of natural images [3], [4], normalized sparse prior [5], framelet based prior [6], l 0 -norm based priors [7], [8], color line prior [9], dark channel prior [10], low rank prior [11] and graph based prior [12], etc. The priors promote image sharpness and penalize image blurriness, which work as a regularizer in the optimization model guiding the solver to converge to the latent sharp image.…”

Section: B Blind Image Deblurringmentioning

confidence: 99%

Single Image Blind Deblurring Using Multi-Scale Latent Structure Prior

Bai

Jia

Jiang

et al. 2019

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Blind image deblurring is a challenging problem in computer vision, which aims to restore both the blur kernel and the latent sharp image from only a blurry observation. Inspired by the prevalent self-example prior in image superresolution, in this paper, we observe that a coarse enough image down-sampled from a blurry observation is approximately a low-resolution version of the latent sharp image. We prove this phenomenon theoretically and define the coarse enough image as a latent structure prior of the unknown sharp image. Starting from this prior, we propose to restore sharp images from the coarsest scale to the finest scale on a blurry image pyramid, and progressively update the prior image using the newly restored sharp image. These coarse-to-fine priors are referred to as Multi-Scale Latent Structures (MSLS). Leveraging the MSLS prior, our algorithm comprises two phases: 1) we first preliminarily restore sharp images in the coarse scales; 2) we then apply a refinement process in the finest scale to obtain the final deblurred image. In each scale, to achieve lower computational complexity, we alternately perform a sharp image reconstruction with fast local self-example matching, an accelerated kernel estimation with error compensation, and a fast non-blind image deblurring, instead of computing any computationally expensive non-convex priors. We further extend the proposed algorithm to solve more challenging non-uniform blind image deblurring problem. Extensive experiments demonstrate that our algorithm achieves competitive results against the state-of-the-art methods with much faster running speed.Index Terms-Blind image deblurring, multi-scale structure, local self-example, uniform and non-uniform deblurring.

show abstract

Blind Image Deblurring Using Dark Channel Prior

Cited by 644 publications

References 25 publications

DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better

DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better

Joint Stereo Video Deblurring, Scene Flow Estimation and Moving Object Segmentation

Single Image Blind Deblurring Using Multi-Scale Latent Structure Prior

Contact Info

Product

Resources

About