253 citations · 310 across the 24 of their papers we have counts for
19 papers · 1 filter
CPDDNet: Color-Polarization Denoising and Demosaicking Network
Qihang Zhang, Yusuke Monno, Masayuki Tanaka +1
Color-polarization imaging using a color-polarization filter array (CPFA) sensor captures both texture (color intensity) and physical (polarization) information of the scene in a s…
Joint 2D-3D Segmentation and Association in Street-level Imaging
Amir Melnikov, Masayuki Tanaka, Yusuke Monno +1
Accurate interpretation of street-level imagery is essential for large-scale urban mapping and the creation of Spatial Digital Twin (SDT) environments. This work presents a unified…
Multi-Modal Pedestrian Detection with Large Misalignment Based on Modal-Wise Regression and Multi-Modal IoU
Napat Wanchaitanawong, Masayuki Tanaka, Takashi Shibata +1
The combined use of multiple modalities enables accurate pedestrian detection under poor lighting conditions by using the high visibility areas from these modalities together. The…
Geometric Data Augmentation Based on Feature Map Ensemble
Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi
Deep convolutional networks have become the mainstream in computer vision applications. Although CNNs have been successful in many computer vision tasks, it is not free from drawba…
Deep Snapshot HDR Imaging Using Multi-Exposure Color Filter Array
Takeru Suda, Masayuki Tanaka, Yusuke Monno +1
In this paper, we propose a deep snapshot high dynamic range (HDR) imaging framework that can effectively reconstruct an HDR image from the RAW data captured using a multi-exposure…
Adaptive Future Frame Prediction with Ensemble Network
Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi +1
Future frame prediction in videos is a challenging problem because videos include complicated movements and large appearance changes. Learning-based future frame prediction approac…
Human Segmentation with Dynamic LiDAR Data
Tao Zhong, Wonjik Kim, Masayuki Tanaka +1
Consecutive LiDAR scans compose dynamic 3D sequences, which contain more abundant information than a single frame. Similar to the development history of image and video perception,…
Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering
Wonjik Kim, Asako Kanezaki, Masayuki Tanaka
The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study. In the proposed approach, label prediction and network paramet…
Classifying degraded images over various levels of degradation
Kazuki Endo, Masayuki Tanaka, Masatoshi Okutomi
Classification for degraded images having various levels of degradation is very important in practical applications. This paper proposes a convolutional neural network to classify…
Learning-Based Human Segmentation and Velocity Estimation Using Automatic Labeled LiDAR Sequence for Training
Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi +1
In this paper, we propose an automatic labeled sequential data generation pipeline for human segmentation and velocity estimation with point clouds. Considering the impact of deep…
Block-wise Scrambled Image Recognition Using Adaptation Network
Koki Madono, Masayuki Tanaka, Masaki Onishi +1
In this study, a perceptually hidden object-recognition method is investigated to generate secure images recognizable by humans but not machines. Hence, both the perceptual informa…
Intentional Attention Mask Transformation for Robust CNN Classification
Masanari Kimura, Masayuki Tanaka
Convolutional Neural Networks have achieved impressive results in various tasks, but interpreting the internal mechanism is a challenging problem. To tackle this problem, we exploi…
Interpretation of Feature Space using Multi-Channel Attentional Sub-Networks
Masanari Kimura, Masayuki Tanaka
Convolutional Neural Networks have achieved impressive results in various tasks, but interpreting the internal mechanism is a challenging problem. To tackle this problem, we exploi…
Automatic Labeled LiDAR Data Generation based on Precise Human Model
Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi +1
Following improvements in deep neural networks, state-of-the-art networks have been proposed for human recognition using point clouds captured by LiDAR. However, the performance of…
Estimation and Restoration of Compositional Degradation Using Convolutional Neural Networks
Kazutaka Uchida, Masayuki Tanaka, Masatoshi Okutomi
Image restoration from a single image degradation type, such as blurring, hazing, random noise, and compression has been investigated for decades. However, image degradations in pr…
Gradient-Based Low-Light Image Enhancement
Masayuki Tanaka, Takashi Shibata, Masatoshi Okutomi
A low-light image enhancement is a highly demanded image processing technique, especially for consumer digital cameras and cameras on mobile phones. In this paper, a gradient-based…
Non-blind Image Restoration Based on Convolutional Neural Network
Kazutaka Uchida, Masayuki Tanaka, Masatoshi Okutomi
Blind image restoration processors based on convolutional neural network (CNN) are intensively researched because of their high performance. However, they are too sensitive to the…
Learnable Image Encryption
Masayuki Tanaka
The network-based machine learning algorithm is very powerful tools. However, it requires huge training dataset. Researchers often meet privacy issues when they collect image datas…
Network Analysis for Explanation
Hiroshi Kuwajima, Masayuki Tanaka
Safety critical systems strongly require the quality aspects of artificial intelligence including explainability. In this paper, we analyzed a trained network to extract features w…