D2S-RSG-SSD: Dual Double-Sampling With Random Sub-Samples Generation for Self-Supervised Real Image Denoising

计算机科学 过度拟合 降噪 人工智能 噪音(视频) 推论 噪声测量 模式识别(心理学) 机器学习 稳健性(进化) 数据挖掘 采样(信号处理) 图像复原 钥匙(锁) 正规化(语言学) 缩小 约束(计算机辅助设计) 计算机视觉 高斯噪声 视频去噪 图像分割 算法 对偶(语法数字)
作者
Xi Liu,Xiuya Shi,Yizhong Pan,Shuhang Gu,Wei Liu,Chao Ren
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:48 (7): 7766-7783
标识
DOI:10.1109/tpami.2026.3665610
摘要

Recent advances in self-supervised image denoising have highlighted the potential of Blind-Spot Networks (BSNs). However, existing methods suffer from three major limitations: (1) Their effectiveness in real-world scenarios is limited by strong assumptions, such as noise independence, which rarely hold in practice. (2) While sampling-based strategies can partially improve performance, BSNs inherently suffer from information loss caused by centroid masking, and removing the blind spot leads to noise overfitting, both of which hinder denoising performance. (3) Sampling-based methods often introduce checkerboard artifacts, yet existing studies typically overlook the fundamental differences between these artifacts and real noise. To address these issues, we propose a novel self-supervised denoising framework, Dual Double-Sampling with Random Sub-samples Generation (D2S-RSG-SSD). To address Limitation 1, we introduce a sampling-based framework that breaks noise dependence by combining Random Sub-samples Generation (RSG) with a cross-paired loss $\mathcal {L}_{RSG}$LRSG. RSG generates diverse sub-samples with inherent variance, referred to as sampling differences, which serve as natural perturbations to augment training data and disrupt spatial noise correlations. The proposed loss function ensures full utilization of these sub-samples while stabilizing optimization. To address Limitation 2, we propose a Dual Double-Sampling (D2S) strategy with fixed sampling patterns and a dual-branch architecture. This design reduces reliance on pixel-level information and leverages complementary features to mitigate both noise overfitting and information loss. A key advantage is its compatibility with various advanced denoising networks, lifting the constraint of using BSNs in self-supervised settings. Additionally, we introduce a fixed sub-image sampling strategy to prevent pattern collapse during inference and ensure stability. To address Limitation 3, we explicitly differentiate checkerboard artifacts from real noise and develop a dedicated artifact remover to correct pixel discontinuities caused by sampling-based operations. This design preserves fine image details while reducing over-smoothing. Experiments on benchmark real-noise datasets and self-captured noisy images demonstrate the robustness and generalizability of our framework, achieving better performance over existing methods.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
思源的应助被放手一搏采纳,获得10
刚刚
小秋发布了新的文献求助10
刚刚
DD完成签到,获得积分10
刚刚
明理的枕头完成签到,获得积分10
刚刚
刚刚
靓靓鱼发布了新的文献求助10
刚刚
无忧sxt发布了新的文献求助10
刚刚
浅浅完成签到,获得积分10
1秒前
1秒前
鱼维尼完成签到,获得积分10
1秒前
1秒前
天天向上的应助被紫薯精采纳,获得10
1秒前
科研通AI6.4的应助被HuBasya采纳,获得10
1秒前
大意的元珊完成签到 ,获得积分10
1秒前
Jimmy Ko完成签到,获得积分10
1秒前
CipherSage的应助被MCFCSH采纳,获得10
2秒前
biu发布了新的文献求助10
2秒前
Ly完成签到,获得积分10
2秒前
2秒前
藏识完成签到,获得积分10
2秒前
nini发布了新的文献求助30
2秒前
ning完成签到,获得积分10
3秒前
dragon发布了新的文献求助10
3秒前
菲菲宋发布了新的文献求助10
3秒前
慧智兰心完成签到,获得积分10
3秒前
任虎完成签到,获得积分10
4秒前
独特的紫雪完成签到,获得积分10
4秒前
orixero的应助被psl采纳,获得10
4秒前
Ava的应助被Solitary采纳,获得20
4秒前
玛卡巴卡完成签到 ,获得积分10
4秒前
易研丁真发布了新的文献求助10
4秒前
上官若男的应助被王梦姣采纳,获得10
5秒前
Owen的应助被闾丘翠桃采纳,获得10
5秒前
一见发布了新的文献求助10
5秒前
开心就吃猕猴桃完成签到,获得积分10
6秒前
6秒前
赘婿的应助被LY采纳,获得10
7秒前
7秒前
阿蒙蒙完成签到 ,获得积分10
7秒前
枫枫不是峰完成签到,获得积分10
7秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180407
求助须知:如何正确求助?哪些是违规求助? 9570403
关于积分的说明 21811831
捐赠科研通 7776452
什么是DOI,文献DOI怎么找? 3433277
关于科研通互助平台的介绍 2557499
邀请新用户注册赠送积分活动 2479105