paper-with-me

홈 › Papers

Discriminative Transfer Learning for General Image Restoration

2017-03-27 · Lei Xiao, Felix Heide, Wolfgang Heidrich, Bernhard Schölkopf, Michael Hirsch

Recently, several discriminative learning approaches have been proposed for effective image restoration, achieving convincing trade-off between image quality and computational efficiency. However, these methods require separate training for each restoration task (e.g., denoising, deblurring, demosaicing) and problem condition (e.g., noise level of input images). This makes it time-consuming and difficult to encompass all tasks and conditions during training. In this paper, we propose a discriminative transfer learning method that incorporates formal proximal optimization and discriminative learning for general image restoration. The method requires a single-pass training and allows for reuse across various problems and conditions while achieving an efficiency comparable to previous discriminative approaches. Furthermore, after being trained, our model can be easily transferred to new likelihood terms to solve untrained tasks, or be combined with existing priors to further improve image restoration quality.

📄 PDF Abstract BibTeX arXiv:1703.09245

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyDeblurringDemosaickingDenoisingImage RestorationTransfer Learning

Similar Papers 제목 키워드 기반

Learning Generic Diffusion Processes for Image Restoration

2018-07-17 · Peng Qiao, Yong Dou, Yunjin Chen, Wensen Feng

Image restoration problems are typical ill-posed problems where the regularization term plays an important role. The regularization term learned via generative approaches is easy to transfer to various image restoration,…

DenoisingImage Restoration

Cascades of Regression Tree Fields for Image Restoration

2014-04-08 · Uwe Schmidt, Jeremy Jancsary, Sebastian Nowozin, Stefan Roth 외

Conditional random fields (CRFs) are popular discriminative models for computer vision and have been successfully applied in the domain of image restoration, especially to image denoising. For image deblurring, however, …

Blind Image DeblurringDeblurringDenoisingImage Deblurring+3

IRConStyle: Image Restoration Framework Using Contrastive Learning and Style Transfer

2024-02-24 · Dongqi Fan, Xin Zhao, Liang Chang

Recently, the contrastive learning paradigm has achieved remarkable success in high-level tasks such as classification, detection, and segmentation. However, contrastive learning applied in low-level tasks, like image re…

Contrastive LearningDeblurringDenoisingImage Restoration+2

UIR-LoRA: Achieving Universal Image Restoration through Multiple Low-Rank Adaptation

2024-09-30 · Cheng Zhang, Dong Gong, Jiumei He, Yu Zhu 외

Existing unified methods typically treat multi-degradation image restoration as a multi-task learning problem. Despite performing effectively compared to single degradation restoration methods, they overlook the utilizat…

Image RestorationMulti-Task LearningTransfer LearningUnified Image Restoration

The Return of the Gating Network: Combining Generative Models and Discriminative Training in Natural Image Priors

2015-12-01 · NeurIPS 2015 12 · Dan Rosenbaum, Yair Weiss

In recent years, approaches based on machine learning have achieved state-of-the-art performance on image restoration problems. Successful approaches include both generative models of natural images as well as discrimina…

Image Restoration