跳到主要导航 跳到搜索 跳到主要内容

YOND: Practical Blind Raw Image Denoising Free from Camera-Specific Data Dependency

  • Hansen Feng
  • , Lizhi Wang*
  • , Yiqi Huang
  • , Tong Li
  • , Lin Zhu
  • , Hua Huang
  • *此作品的通讯作者
  • Beijing Normal University
  • Beijing Institute of Technology

科研成果: 期刊稿件 › 文章 › 同行评审

摘要

The rapid advancement of photography has created a growing demand for a practical blind raw image denoising method. Recently, learning-based methods have become mainstream due to their excellent performance. However, most existing learning-based methods suffer from camera-specific data dependency, resulting in performance drops when applied to data from unknown cameras. To address this challenge, we introduce a novel blind raw image denoising method named YOND, which represents You Only Need a Denoiser. Trained solely on synthetic data, YOND can generalize robustly to noisy raw images captured by diverse unknown cameras. Specifically, we propose three key modules to guarantee the practicality of YOND: coarse-to-fine noise estimation (CNE), expectationmatched variance-stabilizing transform (EM-VST), and SNRguided denoiser (SNR-Net). Firstly, we propose CNE to identify the camera noise characteristic, refining the estimated noise parameters based on the coarse denoised image. Secondly, we propose EM-VST to eliminate camera-specific data dependency, correcting the bias expectation of VST according to the noisy image. Finally, we propose SNR-Net to offer controllable raw image denoising, supporting adaptive adjustments and manual fine-tuning. Extensive experiments on unknown cameras, along with flexible solutions for challenging cases, demonstrate the superior practicality of our method.

源语言英语
期刊IEEE Transactions on Pattern Analysis and Machine Intelligence
DOI
出版状态已接受/待刊 - 2026
已对外发布是

学术指纹

探究 'YOND: Practical Blind Raw Image Denoising Free from Camera-Specific Data Dependency' 的科研主题。它们共同构成独一无二的学术指纹。

引用此