activity
20172022
most citedOutlier Cluster Formation in Spectral Clustering

1 citations · 3 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CV2022

Deep Depth from Focal Stack with Defocus Model for Camera-Setting Invariance

Yuki Fujimura, Masaaki Iiyama, Takuya Funatomi +1

We propose a learning-based depth from focus/defocus (DFF), which takes a focal stack as input for estimating scene depth. Defocus blur is a useful cue for depth estimation. Howeve…

cs.CV20201 cited

Dehazing Cost Volume for Deep Multi-view Stereo in Scattering Media with Airlight and Scattering Coefficient Estimation

Yuki Fujimura, Motoharu Sonogashira, Masaaki Iiyama

We propose a learning-based multi-view stereo (MVS) method in scattering media, such as fog or smoke, with a novel cost volume, called the dehazing cost volume. Images captured in…

cs.CV20201 cited

Partially-Shared Variational Auto-encoders for Unsupervised Domain Adaptation with Target Shift

Ryuhei Takahashi, Atsushi Hashimoto, Motoharu Sonogashira +1

This paper proposes a novel approach for unsupervised domain adaptation (UDA) with target shift. Target shift is a problem of mismatch in label distribution between source and targ…

cs.CV2019

Defogging Kinect: Simultaneous Estimation of Object Region and Depth in Foggy Scenes

Yuki Fujimura, Motoharu Sonogashira, Masaaki Iiyama

Three-dimensional (3D) reconstruction and scene depth estimation from 2-dimensional (2D) images are major tasks in computer vision. However, using conventional 3D reconstruction te…

cs.CV2018

Photometric Stereo in Participating Media Considering Shape-Dependent Forward Scatter

Yuki Fujimura, Masaaki Iiyama, Atsushi Hashimoto +1

Images captured in participating media such as murky water, fog, or smoke are degraded by scattered light. Thus, the use of traditional three-dimensional (3D) reconstruction techni…

cs.CV20171 cited

Outlier Cluster Formation in Spectral Clustering

Takuro Ina, Atsushi Hashimoto, Masaaki Iiyama +3

Outlier detection and cluster number estimation is an important issue for clustering real data. This paper focuses on spectral clustering, a time-tested clustering method, and reve…