paper-with-me

홈 › Papers

Automatic Tuning of Denoising Algorithms Parameters Without Ground Truth

2024-01-18 · Arthur Floquet, Sayantan Dutta, Emmanuel Soubies, Duong Hung Pham, Denis Kouame

Denoising is omnipresent in image processing. It is usually addressed with algorithms relying on a set of hyperparameters that control the quality of the recovered image. Manual tuning of those parameters can be a daunting task, which calls for the development of automatic tuning methods. Given a denoising algorithm, the best set of parameters is the one that minimizes the error between denoised and ground-truth images. Clearly, this ideal approach is unrealistic, as the ground-truth images are unknown in practice. In this work, we propose unsupervised cost functions -- i.e., that only require the noisy image -- that allow us to reach this ideal gold standard performance. Specifically, the proposed approach makes it possible to obtain an average PSNR output within less than 1% of the best achievable PSNR.

📄 PDF Abstract BibTeX arXiv:2401.09817

Code (1)

https://gitlab.com/a_floquet/automatic-tuning-of-denoising-algorithms-parameters-without-ground-truth 공식 구현 pytorch

Tasks

Denoising

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Image Restoration by Iterative Denoising and Backward Projections

2017-10-18 · Tom Tirer, Raja Giryes

Inverse problems appear in many applications, such as image deblurring and inpainting. The common approach to address them is to design a specific algorithm for each problem. The Plug-and-Play (P&P) framework, which has …

DeblurringDenoisingImage DeblurringImage Inpainting+1

Deep learning for denoising

2018-10-27 · Siwei Yu, Jianwei Ma, Wenlong Wang

Compared with traditional seismic noise attenuation algorithms that depend on signal models and their corresponding prior assumptions, removing noise with a deep neural network is trained based on a large training set, w…

Deep LearningDenoising

TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems

2020-11-18 · Kaixuan Wei, Angelica Aviles-Rivero, Jingwei Liang, Ying Fu 외

Plug-and-Play (PnP) is a non-convex optimization framework that combines proximal algorithms, for example, the alternating direction method of multipliers (ADMM), with advanced denoising priors. Over the past few years, …

compressed sensingDeep Reinforcement LearningDenoisingRetrieval

Automatic ISP image quality tuning using non-linear optimization

2019-02-24 · Jun Nishimura, Timo Gerasimow, Sushma Rao, Aleksandar Sutic 외

Image Signal Processor (ISP) comprises of various blocks to reconstruct image sensor raw data to final image consumed by human visual system or computer vision applications. Each block typically has many tuning parameter…

Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems

2020-02-22 · ICML 2020 1 · Kaixuan Wei, Angelica Aviles-Rivero, Jingwei Liang, Ying Fu 외

Plug-and-play (PnP) is a non-convex framework that combines ADMM or other proximal algorithms with advanced denoiser priors. Recently, PnP has achieved great empirical success, especially with the integration of deep lea…

compressed sensingDeep Reinforcement LearningDenoisingReinforcement Learning+1