Deblurring Photographs of Characters Using Deep Neural Networks

• URL: http://arxiv.org/abs/2205.15053v2
• Date: Tue, 31 May 2022 07:45:45 GMT
• Title: Deblurring Photographs of Characters Using Deep Neural Networks
• Authors: Thomas Germer, Tobias Uelwer and Stefan Harmeling
• Abstract summary: We present our approach for the Helsinki Deblur Challenge (HDC 2021) The challenge is to deblur images of characters without knowing the point spread function (PSF) Our method consists of three steps: first, we estimate a warping transformation of the images to align the sharp images with the blurred ones; second, we estimate the PSF using a quasi-Newton method; third, we train a deep convolutional neural network to reconstruct the sharp images from the blurred images.
• Score: 0.5156484100374059
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we present our approach for the Helsinki Deblur Challenge (HDC2021). The task of this challenge is to deblur images of characters without knowing the point spread function (PSF). The organizers provided a dataset of pairs of sharp and blurred images. Our method consists of three steps: First, we estimate a warping transformation of the images to align the sharp images with the blurred ones. Next, we estimate the PSF using a quasi-Newton method. The estimated PSF allows to generate additional pairs of sharp and blurred images. Finally, we train a deep convolutional neural network to reconstruct the sharp images from the blurred images. Our method is able to successfully reconstruct images from the first 10 stages of the HDC 2021 data. Our code is available at https://github.com/hhu-machine-learning/hdc2021-psfnn.

Related papers

• LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network [20.42001628066274]
  We introduce the contrastive language-image pre-training framework (CLIP) to accurately estimate the blur map from a DP pair unsupervisedly. Our method achieves state-of-the-art performance in extensive experiments.
  arXiv  Detail & Related papers  (2023-07-19T08:03:53Z)
• 1st Solution Places for CVPR 2023 UG$^2$+ Challenge Track 2.2-Coded Target Restoration through Atmospheric Turbulence [12.484269899245515]
  This report introduces the solution of our team VIELab-HUST for coded target restoration through atmospheric turbulence in CVPR 2023 UG$2$+ Track 2.2. We propose an efficient multi-stage framework to restore a high quality image from distorted frames. Our framework is capable of handling different kinds of coded target dataset provided in the final testing phase, and ranked 1st on the final leaderboard.
  arXiv  Detail & Related papers  (2023-06-15T09:06:48Z)
• NBD-GAP: Non-Blind Image Deblurring Without Clean Target Images [79.33220095067749]
  Large amounts of blurry-clean image pairs are required for training to achieve good performance. Deep networks often fail to perform well when the blurry images and the blur kernels during testing are very different from the ones used during training.
  arXiv  Detail & Related papers  (2022-09-20T06:21:11Z)
• Deep Facial Synthesis: A New Challenge [75.99659340231078]
  We first introduce a high-quality dataset for FSS, named FS2K, which consists of 2,104 image-sketch pairs. Second, we present the largest-scale FSS study by investigating 139 classical methods. Third, we present a simple baseline for FSS, named FSGAN.
  arXiv  Detail & Related papers  (2021-12-31T13:19:21Z)
• Is Deep Image Prior in Need of a Good Education? [57.3399060347311]
  Deep image prior was introduced as an effective prior for image reconstruction. Despite its impressive reconstructive properties, the approach is slow when compared to learned or traditional reconstruction techniques. We develop a two-stage learning paradigm to address the computational challenge.
  arXiv  Detail & Related papers  (2021-11-23T15:08:26Z)
• Single image deep defocus estimation and its applications [82.93345261434943]
  We train a deep neural network to classify image patches into one of the 20 levels of blurriness. The trained model is used to determine the patch blurriness which is then refined by applying an iterative weighted guided filter. The result is a defocus map that carries the information of the degree of blurriness for each pixel.
  arXiv  Detail & Related papers  (2021-07-30T06:18:16Z)
• Beyond Joint Demosaicking and Denoising: An Image Processing Pipeline for a Pixel-bin Image Sensor [0.883717274344425]
  Pixel binning is considered one of the most prominent solutions to tackle the hardware limitation of smartphone cameras. In this paper, we tackle the challenges of joint demosaicing and denoising (JDD) on such an image sensor by introducing a novel learning-based method. The proposed method is guided by a multi-term objective function, including two novel perceptual losses to produce visually plausible images.
  arXiv  Detail & Related papers  (2021-04-19T15:41:28Z)
• Deep Artifact-Free Residual Network for Single Image Super-Resolution [0.2399911126932526]
  We propose Deep Artifact-Free Residual (DAFR) network which uses the merits of both residual learning and usage of ground-truth image as target. Our framework uses a deep model to extract the high-frequency information which is necessary for high-quality image reconstruction. Our experimental results show that the proposed method achieves better quantitative and qualitative image quality compared to the existing methods.
  arXiv  Detail & Related papers  (2020-09-25T20:53:55Z)
• SCAN: Learning to Classify Images without Labels [73.69513783788622]
  We advocate a two-step approach where feature learning and clustering are decoupled. A self-supervised task from representation learning is employed to obtain semantically meaningful features. We obtain promising results on ImageNet, and outperform several semi-supervised learning methods in the low-data regime.
  arXiv  Detail & Related papers  (2020-05-25T18:12:33Z)
• Self-Supervised Linear Motion Deblurring [112.75317069916579]
  Deep convolutional neural networks are state-of-the-art for image deblurring. We present a differentiable reblur model for self-supervised motion deblurring. Our experiments demonstrate that self-supervised single image deblurring is really feasible.
  arXiv  Detail & Related papers  (2020-02-10T20:15:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.