Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Yi Luo

Yi Luo

Department of Electrical Engineering, Columbia University, NY, USA

On the Use of Deep Mask Estimation Module for Neural Source Separation Systems



Kai Li , Xiaolin Hu , Yi Luo

Figure 1 for On the Use of Deep Mask Estimation Module for Neural Source Separation Systems
Figure 2 for On the Use of Deep Mask Estimation Module for Neural Source Separation Systems
Figure 3 for On the Use of Deep Mask Estimation Module for Neural Source Separation Systems
Figure 4 for On the Use of Deep Mask Estimation Module for Neural Source Separation Systems
* Accepted by Interspeech 2022 
   Access Paper or Ask Questions

On the Design and Training Strategies for RNN-based Online Neural Speech Separation Systems



Kai Li , Yi Luo

Figure 1 for On the Design and Training Strategies for RNN-based Online Neural Speech Separation Systems
Figure 2 for On the Design and Training Strategies for RNN-based Online Neural Speech Separation Systems
Figure 3 for On the Design and Training Strategies for RNN-based Online Neural Speech Separation Systems
* 5 pages, 1 figure 
   Access Paper or Ask Questions

Super-resolution image display using diffractive decoders



Cagatay Isil , Deniz Mengu , Yifan Zhao , Anika Tabassum , Jingxi Li , Yi Luo , Mona Jarrahi , Aydogan Ozcan

Figure 1 for Super-resolution image display using diffractive decoders
Figure 2 for Super-resolution image display using diffractive decoders
Figure 3 for Super-resolution image display using diffractive decoders
Figure 4 for Super-resolution image display using diffractive decoders
* 26 Pages, 9 Figures 
   Access Paper or Ask Questions

To image, or not to image: Class-specific diffractive cameras with all-optical erasure of undesired objects



Bijie Bai , Yi Luo , Tianyi Gan , Jingtian Hu , Yuhang Li , Yifan Zhao , Deniz Mengu , Mona Jarrahi , Aydogan Ozcan

Figure 1 for To image, or not to image: Class-specific diffractive cameras with all-optical erasure of undesired objects
Figure 2 for To image, or not to image: Class-specific diffractive cameras with all-optical erasure of undesired objects
Figure 3 for To image, or not to image: Class-specific diffractive cameras with all-optical erasure of undesired objects
Figure 4 for To image, or not to image: Class-specific diffractive cameras with all-optical erasure of undesired objects
* 31 Pages, 7 Figures 
   Access Paper or Ask Questions

Analysis of Diffractive Neural Networks for Seeing Through Random Diffusers



Yuhang Li , Yi Luo , Bijie Bai , Aydogan Ozcan

Figure 1 for Analysis of Diffractive Neural Networks for Seeing Through Random Diffusers
Figure 2 for Analysis of Diffractive Neural Networks for Seeing Through Random Diffusers
Figure 3 for Analysis of Diffractive Neural Networks for Seeing Through Random Diffusers
Figure 4 for Analysis of Diffractive Neural Networks for Seeing Through Random Diffusers
* 42 Pages, 9 Figures 
   Access Paper or Ask Questions

Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization



Wei Dong , Junsheng Wu , Yi Luo , Zongyuan Ge , Peng Wang

Figure 1 for Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization
Figure 2 for Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization
Figure 3 for Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization
Figure 4 for Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization
* Paper is accepted to CVPR 2022. Codes and supplementary materials are available at https://github.com/dongwei156/n2n 
   Access Paper or Ask Questions

A Time-domain Generalized Wiener Filter for Multi-channel Speech Separation



Yi Luo

Figure 1 for A Time-domain Generalized Wiener Filter for Multi-channel Speech Separation
Figure 2 for A Time-domain Generalized Wiener Filter for Multi-channel Speech Separation
Figure 3 for A Time-domain Generalized Wiener Filter for Multi-channel Speech Separation
Figure 4 for A Time-domain Generalized Wiener Filter for Multi-channel Speech Separation

   Access Paper or Ask Questions

Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network



Xiaolin Hu , Kai Li , Weiyi Zhang , Yi Luo , Jean-Marie Lemercier , Timo Gerkmann

Figure 1 for Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network
Figure 2 for Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network
Figure 3 for Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network
Figure 4 for Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network
* Accepted by NeurIPS 2021, Demo at https://cslikai.cn/project/AFRCNN 
   Access Paper or Ask Questions

Cascadable all-optical NAND gates using diffractive networks



Yi Luo , Deniz Mengu , Aydogan Ozcan

Figure 1 for Cascadable all-optical NAND gates using diffractive networks
Figure 2 for Cascadable all-optical NAND gates using diffractive networks
Figure 3 for Cascadable all-optical NAND gates using diffractive networks
Figure 4 for Cascadable all-optical NAND gates using diffractive networks
* 24 Pages, 5 Figures 
   Access Paper or Ask Questions

Computational Imaging Without a Computer: Seeing Through Random Diffusers at the Speed of Light



Yi Luo , Yifan Zhao , Jingxi Li , Ege Cetintas , Yair Rivenson , Mona Jarrahi , Aydogan Ozcan

Figure 1 for Computational Imaging Without a Computer: Seeing Through Random Diffusers at the Speed of Light
Figure 2 for Computational Imaging Without a Computer: Seeing Through Random Diffusers at the Speed of Light
Figure 3 for Computational Imaging Without a Computer: Seeing Through Random Diffusers at the Speed of Light
Figure 4 for Computational Imaging Without a Computer: Seeing Through Random Diffusers at the Speed of Light
* 35 Pages, 7 Figures 
   Access Paper or Ask Questions
1
2
3
4
>>