All-Optical Nonlinear Diffractive Deep Network for Ultrafast Image Denoising
Xiaoling Zhou, Zhemg Lee, Wei Ye, Rui Xie, Wenbo Zhang, Guanju Peng, Zongze Li, Shikun Zhang
Abstract
Image denoising poses a significant challenge in image processing, aiming to remove noise and artifacts from input images. However, current denoising algorithms implemented on electronic chips frequently encounter latency issues and demand substantial computational resources. In this paper, we introduce an all-optical Nonlinear Diffractive Denoising Deep Network (N3DNet) for image denoising at the speed of light. Initially, we incorporate an image encoding and pre-denoising module into the Diffractive Deep Neural Network and integrate a nonlinear activation function, termed the phase exponential linear function, after each diffractive layer, thereby boosting the network's nonlinear modeling and denoising capabilities. Subsequently, we devise a new reinforcement learning algorithm called regularization-assisted deep Q-network to optimize N3DNet. Finally, leveraging 3D printing techniques, we fabricate N3DNet using the trained parameters and construct a physical experimental system for real-world applications. A new benchmark dataset, termed MIDD, is constructed for mode image denoising, comprising 120K pairs of noisy/noise-free images captured from real fiber communication systems across various transmission lengths. Through extensive simulation and real experiments, we validate that N3DNet outperforms both traditional and deep learning-based denoising approaches across various datasets. Remarkably, its processing speed is nearly 3,800 times faster than electronic chip-based methods.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on4
- Real Image Denoising With Feature AttentionSaeed Anwar, Nick BarnesICCV 2019 · 644 citations
- Interactive Monte Carlo denoising using affinity of neural featuresMustafa Isik, Krishna Mullia, Matthew Fisher, Jonathan Eisenmann et al.SIGGRAPH 2021 · 50 citations
- Self2Self With Dropout: Learning Self-Supervised Denoising From Single ImageYuhui Quan, Mingqin Chen, Tongyao Pang, Hui JiCVPR 2020
- Masked Image Training for Generalizable Deep Image DenoisingHaoyu Chen, Jinjin Gu, Yihao Liu, Salma Abdel Magid et al.CVPR 2023
Related papers
- Optical Diffusion Models for Image GenerationIlker Oguz, Niyazi Ulas Dinç, Mustafa Yildirim, Junjie Ke et al.NeurIPS 2024 · 10 citations
- Physics-aware Roughness Optimization for Diffractive Optical Neural NetworksShanglin Zhou, Yingjie Li, Minhan Lou, Weilu Gao et al.DAC 2023 · 1 citation
- Real-World Mobile Image Denoising Dataset with Efficient BaselinesRoman Flepp, Andrey Ignatov, Radu Timofte, Luc Van GoolCVPR 2024
- FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow EstimationMatias Tassano, Julie Delon, Thomas VeitCVPR 2020
- Effectively Learning Moiré QR Code Decryption from Simulated DataYu Lu, Hao Pan, Feitong Tan, Yi-Chao Chen et al.INFOCOM 2023 · 3 citations
