Non-uniform Blind Deblurring by Reblurring

Bahat, Yuval; Efrat, Netalee; Irani, Michal

doi:10.1109/iccv.2017.356

Cited by 86 publications

(54 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Geometry-based methods. Modern single-image deblurring methods iteratively estimate uniform or non-uniform blur kernels and the latent sharp image given a single blurry image [9], [10], [11], [12], [13], [14], [15], [16], [17], [18], [19], [20]. However, it is difficult for single image based methods to estimate kernel because blur is spatially varying in real world.…”

Section: Related Workmentioning

confidence: 99%

Adversarial Spatio-Temporal Learning for Video Deblurring

Zhang

Luo

Zhong

et al. 2019

IEEE Trans. on Image Process.

149

View full text Add to dashboard Cite

Camera shake or target movement often leads to undesired blur effects in videos captured by a hand-held camera. Despite significant efforts having been devoted to video-deblur research, two major challenges remain: 1) how to model the spatio-temporal characteristics across both the spatial domain (i.e., image plane) and the temporal domain (i.e., neighboring frames) and 2) how to restore sharp image details with respect to the conventionally adopted metric of pixel-wise errors. In this paper, to address the first challenge, we propose a deblurring network (DBLRNet) for spatial-temporal learning by applying a 3D convolution to both the spatial and temporal domains. Our DBLRNet is able to capture jointly spatial and temporal information encoded in neighboring frames, which directly contributes to the improved video deblur performance. To tackle the second challenge, we leverage the developed DBLRNet as a generator in the generative adversarial network (GAN) architecture and employ a content loss in addition to an adversarial loss for efficient adversarial training. The developed network, which we name as deblurring GAN, is tested on two standard benchmarks and achieves the state-of-the-art performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Adversarial Spatio-Temporal Learning for Video Deblurring

Zhang

Luo

Zhong

et al. 2019

IEEE Trans. on Image Process.

149

View full text Add to dashboard Cite

show abstract

“…By comparing the blurred original images with the outputs of CAE, the boundary between the HF and LF is located, making it convenient to conduct combination of the HF and LF of the original images and CAE outputs respectively. The re-blurry strategy performs well in image quality assessment [32], [33] and de-blurring [34], [35]. Taking the corresponding re-blurred restored results as references to the original images, parameters in these algorithms are fine-tuned and optimized results are achieved.…”

Section: Related Workmentioning

confidence: 99%

High-Fidelity Illumination Normalization for Face Recognition Based on Auto-Encoder

Wang

2020

IEEE Access

View full text Add to dashboard Cite

Nonuniform illumination is one of the main issues that hinder the accuracy of face recognition because it makes the intra-person variation more complicated. To minimize the intra-person differences caused by varying illuminations, this paper presents a normalization method based on Convolutional Auto-encoder (CAE). The CAE is employed to map the face images under various illumination conditions to a normalized one, generating preliminary results with blurry and insufficient facial details, which are tricky for recognition. To recover these details, a restoration method based on re-blurring strategy and frequency analysis is proposed to preserve the facial features lying in high-frequency components based on discrete cosine transform (DCT). Therefore, in our method, these components are extracted and reintroduced into the outputs of CAE to enhance the fidelity of outputs. Thus, the facial details are preserved to the largest degree and the following works such as recognition tasks are benefited. Experiments conducted on the AR, extended Yale B, and CAS-PEAL database demonstrate the effectiveness of our method.

show abstract

“…An advantage of DL-based methods is their ability to implicitly learn the statistics of natural images. Moreover, recent research has demonstrated that CNNs are inherently good at generating high-quality images, even when operating outside the supervised learning regime, e.g., [24] and [25].…”

Section: Introductionmentioning

confidence: 99%

DeepISP: Toward Learning an End-to-End Image Processing Pipeline

Schwartz

Giryes

Bronstein

2019

IEEE Trans. on Image Process.

208

132

View full text Add to dashboard Cite

We present DeepISP, a full end-to-end deep neural model of the camera image signal processing (ISP) pipeline. Our model learns a mapping from the raw low-light mosaiced image to the final visually compelling image and encompasses low-level tasks such as demosaicing and denoising as well as higher-level tasks such as color correction and image adjustment. The training and evaluation of the pipeline were performed on a dedicated dataset containing pairs of low-light and well-lit images captured by a Samsung S7 smartphone camera in both raw and processed JPEG formats. The proposed solution achieves state-of-the-art performance in objective evaluation of PSNR on the subtask of joint denoising and demosaicing. For the full end-to-end pipeline, it achieves better visual quality compared to the manufacturer ISP, in both a subjective human assessment and when rated by a deep model trained for assessing image quality.

show abstract

Non-uniform Blind Deblurring by Reblurring

Cited by 86 publications

References 16 publications

Adversarial Spatio-Temporal Learning for Video Deblurring

Adversarial Spatio-Temporal Learning for Video Deblurring

High-Fidelity Illumination Normalization for Face Recognition Based on Auto-Encoder

DeepISP: Toward Learning an End-to-End Image Processing Pipeline

Contact Info

Product

Resources

About