activity
20192025
most citedPartially-Shared Variational Auto-encoders for Unsupervised Domain Adaptation with Target Shift

1 citations · 3 across the 4 of their papers we have counts for

collaborators

5 papers

cs.CV2025

FROSS: Faster-than-Real-Time Online 3D Semantic Scene Graph Generation from RGB-D Images

Hao-Yu Hou, Chun-Yi Lee, Motoharu Sonogashira +1

The ability to abstract complex 3D environments into simplified and structured representations is crucial across various domains. 3D semantic scene graphs (SSGs) achieve this by re…

cs.CV2023★ 1 cited

ManifoldNeRF: View-dependent Image Feature Supervision for Few-shot Neural Radiance Fields

Daiju Kanaoka, Motoharu Sonogashira, Hakaru Tamukoh +1

Novel view synthesis has recently made significant progress with the advent of Neural Radiance Fields (NeRF). DietNeRF is an extension of NeRF that aims to achieve this task from o…

cs.CV2020★ 1 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.CV2020★ 1 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…