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