paper-with-me

Papers

Zero-shot Blind Image Denoising via Implicit Neural Representations

2022-04-05 · Chaewon Kim, Jaeho Lee, Jinwoo Shin

Recent denoising algorithms based on the "blind-spot" strategy show impressive blind image denoising performances, without utilizing any external dataset. While the methods excel in recovering highly contaminated images, we observe that such algorithms are often less effective under a low-noise or real noise regime. To address this gap, we propose an alternative denoising strategy that leverages the architectural inductive bias of implicit neural representations (INRs), based on our two findings: (1) INR tends to fit the low-frequency clean image signal faster than the high-frequency noise, and (2) INR layers that are closer to the output play more critical roles in fitting higher-frequency parts. Building on these observations, we propose a denoising algorithm that maximizes the innate denoising capability of INRs by penalizing the growth of deeper layer weights. We show that our method outperforms existing zero-shot denoising methods under an extensive set of low-noise or real-noise scenarios.

📄 PDF Abstract BibTeX arXiv:2204.02405

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingImage DenoisingInductive Bias

Similar Papers 제목 키워드 기반

Zero-Shot Blind-spot Image Denoising via Implicit Neural Sampling

2025-01-01 · CVPR 2025 1 · Yuhui Quan, Tianxiang Zheng, Zhiyuan Ma, Hui Ji

The blind-spot principle has been a widely used tool in zero-shot image denoising but faces challenges with real-world noise that exhibits strong local correlations. Existing methods focus on reducing noise correlati…

DenoisingImage Denoising

Domino Denoise: An Accurate Blind Zero-Shot Denoiser using Domino Tilings

2022-12-05 · Jason Lequyer, Wen-Hsin Hsu, Reuben Philip, Anna Christina Erpf 외

Because noise can interfere with downstream analysis, image denoising has come to occupy an important place in the image processing toolbox. The most accurate state-of-the-art denoisers typically train on a representativ…

DenoisingImage Denoising

Low-Trace Adaptation of Zero-shot Self-supervised Blind Image Denoising

2024-03-19 · Jintong Hu, Bin Xia, Bingchen Li, Wenming Yang

Deep learning-based denoiser has been the focus of recent development on image denoising. In the past few years, there has been increasing interest in developing self-supervised denoising networks that only require noisy…

DenoisingImage DenoisingSelf-Supervised Learning

Noise2Kernel: Adaptive Self-Supervised Blind Denoising using a Dilated Convolutional Kernel Architecture

2020-12-07 · Kanggeun Lee, Won-Ki Jeong

With the advent of recent advances in unsupervised learning, efficient training of a deep network for image denoising without pairs of noisy and clean images has become feasible. However, most current unsupervised denois…

DenoisingImage Denoising

Pseudo-Siamese Blind-Spot Transformers for Self-Supervised Real-World Denoising

2025-06-05 · The Annual Conference on Neural Information Processing Systems 2025 6 · Yuhui Quan; Tianxiang Zheng; Hui Ji

Real-world image denoising remains a challenge task. This paper studies self-supervised image denoising, requiring only noisy images captured in a single shot. We revamping the blind-spot technique by leveraging the tran…

DenoisingImage Denoising