paper-with-me

홈 › Papers

Functional Neural Networks for Parametric Image Restoration Problems

2021-10-30 · NeurIPS 2021 12 · Fangzhou Luo, Xiaolin Wu, Yanhui Guo

Almost every single image restoration problem has a closely related parameter, such as the scale factor in super-resolution, the noise level in image denoising, and the quality factor in JPEG deblocking. Although recent studies on image restoration problems have achieved great success due to the development of deep neural networks, they handle the parameter involved in an unsophisticated way. Most previous researchers either treat problems with different parameter levels as independent tasks, and train a specific model for each parameter level; or simply ignore the parameter, and train a single model for all parameter levels. The two popular approaches have their own shortcomings. The former is inefficient in computing and the latter is ineffective in performance. In this work, we propose a novel system called functional neural network (FuncNet) to solve a parametric image restoration problem with a single model. Unlike a plain neural network, the smallest conceptual element of our FuncNet is no longer a floating-point variable, but a function of the parameter of the problem. This feature makes it both efficient and effective for a parametric problem. We apply FuncNet to super-resolution, image denoising, and JPEG deblocking. The experimental results show the superiority of our FuncNet on all three parametric image restoration tasks over the state of the arts.

📄 PDF Abstract BibTeX arXiv:2111.00361

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingImage DenoisingImage RestorationSuper-Resolution

Similar Papers 제목 키워드 기반

Image Segmentation and Restoration Using Parametric Contours With Free Endpoints

2015-04-27 · Heike Benninghoff, Harald Garcke

In this paper, we introduce a novel approach for active contours with free endpoints. A scheme is presented for image segmentation and restoration based on a discrete version of the Mumford-Shah functional where the cont…

DenoisingImage SegmentationSegmentationSemantic Segmentation

A Restoration Network as an Implicit Prior

2023-10-02 · Yuyang Hu, Mauricio Delbracio, Peyman Milanfar, Ulugbek S. Kamilov

Image denoisers have been shown to be powerful priors for solving inverse problems in imaging. In this work, we introduce a generalization of these methods that allows any image restoration network to be used as an impli…

Image RestorationSuper-Resolution

Fast image segmentation and restoration using parametric curve evolution with junctions and topology changes

2013-08-10 · Heike Benninghoff, Harald Garcke

Curve evolution schemes for image segmentation based on a region based contour model allowing for junctions, vector-valued images and topology changes are introduced. Together with an a posteriori denoising in the segmen…

DenoisingImage SegmentationSegmentationSemantic Segmentation

Image Restoration from Parametric Transformations using Generative Models

2020-05-27 · Kalliopi Basioti, George V. Moustakides

When images are statistically described by a generative model we can use this information to develop optimum techniques for various image restoration problems as inpainting, super-resolution, image coloring, generative m…

Blind Image DeblurringColorizationDeblurringImage Restoration+1

Segmentation and Restoration of Images on Surfaces by Parametric Active Contours with Topology Changes

2015-05-01 · Heike Benninghoff, Harald Garcke

In this article, a new method for segmentation and restoration of images on two-dimensional surfaces is given. Active contour models for image segmentation are extended to images on surfaces. The evolving curves on the s…

Image RestorationImage SegmentationSegmentationSemantic Segmentation