paper-with-me

Papers

Deep Hybrid Scattering Image Learning

2018-09-19 · Mu Yang, Zheng-Hao Liu, Ze-Di Cheng, Jin-Shi Xu, Chuan-Feng Li, Guang-Can Guo

A well-trained deep neural network is shown to gain capability of simultaneously restoring two kinds of images, which are completely destroyed by two distinct scattering medias respectively. The network, based on the U-net architecture, can be trained by blended dataset of speckles-reference images pairs. We experimentally demonstrate the power of the network in reconstructing images which are strongly diffused by glass diffuser or multi-mode fiber. The learning model further shows good generalization ability to reconstruct images that are distinguished from the training dataset. Our work facilitates the study of optical transmission and expands machine learning's application in optics.

📄 PDF Abstract BibTeX arXiv:1809.07706

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Scattering Networks for Hybrid Representation Learning

2018-09-17 · Edouard Oyallon, Sergey Zagoruyko, Gabriel Huang, Nikos Komodakis 외

Scattering networks are a class of designed Convolutional Neural Networks (CNNs) with fixed weights. We argue they can serve as generic representations for modelling images. In particular, by working in scattering space,…

Representation Learning

Scaling the Scattering Transform: Deep Hybrid Networks

2017-03-27 · ICCV 2017 10 · Edouard Oyallon, Eugene Belilovsky, Sergey Zagoruyko

We use the scattering network as a generic and fixed ini-tialization of the first layers of a supervised hybrid deep network. We show that early layers do not necessarily need to be learned, providing the best results to…

Image Classification

3DeepCT: Learning Volumetric Scattering Tomography of Clouds

2021-01-01 · ICCV 2021 10 · Yael Sde-Chen, Yoav Y. Schechner, Vadim Holodovsky, Eshkol Eytan

We present 3DeepCT, a deep neural network for computed tomography, which performs 3D reconstruction of scattering volumes from multi-view images. The architecture is dictated by the stationary nature of atmospheric c…

3D Reconstruction

Efficient Hybrid Network: Inducting Scattering Features

2022-03-29 · Dmitry Minskiy, Miroslaw Bober

Recent work showed that hybrid networks, which combine predefined and learnt filters within a single architecture, are more amenable to theoretical analysis and less prone to overfitting in data-limited scenarios. Howeve…

3D Scattering Tomography by Deep Learning with Architecture Tailored to Cloud Fields

2020-12-10 · Yael Sde-Chen, Yoav Y. Schechner, Vadim Holodovsky, Eshkol Eytan

We present 3DeepCT, a deep neural network for computed tomography, which performs 3D reconstruction of scattering volumes from multi-view images. Our architecture is dictated by the stationary nature of atmospheric cloud…

3D Reconstruction