Hitotsubashi University
School of Social Data Science
Graphics and Vision Labratory

Projects

This page presents specific research projects published by our lab.

Filter projects by research area using the buttons below.

NeMCoF: Neural Material Composition Fields for Material Decomposition in Sparse-View Spectral X-ray CT

NDT

applications

NeMCoF: Neural Material Composition Fields for Material Decomposition in Sparse-View Spectral X-ray CT

Reference: Takumi Hotta, Tatsuya Yatagawa, Yutaka Ohtake, Toru Aoki, “NeMCoF: Neural Material Composition Fields for Material Decomposition in Sparse-View Spectral X-ray CT,” Journal of Nondestructive Evaluation (2025).

Towards accelerating polarization path tracing of multi-bounce Smith microfacet BSDFs

graphics

rendering

Towards accelerating polarization path tracing of multi-bounce Smith microfacet BSDFs

Reference: Hidehito Ohba, Tatsuya Yatagawa, Shigeo Morishima, “Towards accelerating polarization path tracing of multi-bounce Smith microfacet BSDFs,” (2025).

Learning Scatter Artifact Correction in Cone-Beam X-Ray CT Using Incomplete Projections with Beam Hole Array

NDT

applications

Learning Scatter Artifact Correction in Cone-Beam X-Ray CT Using Incomplete Projections with Beam Hole Array

Reference: Haruki Hattori, Tatsuya Yatagawa, Yutaka Ohtake, Hiromasa Suzuki, “Learning Scatter Artifact Correction in Cone-Beam X-Ray CT Using Incomplete Projections with Beam Hole Array,” Journal of Nondestructive Evaluation (2024).

X-ray 3D Fiber Orientation Tomography via Alternating Optimization of Scattering Coefficients and Directions

NDT

applications

X-ray 3D Fiber Orientation Tomography via Alternating Optimization of Scattering Coefficients and Directions

Reference: Tomoki Mori, Yutaka Ohtake, Tatsuya Yatagawa, Kazuhiro Kido, Yasunori Tsuboi, “X-ray 3D Fiber Orientation Tomography via Alternating Optimization of Scattering Coefficients and Directions,” Journal of Nondestructive Evaluation (2024).

Learning Self-Prior for Mesh Inpainting Using Self-Supervised Graph Convolutional Networks

graphics

geometry

deep learning

Learning Self-Prior for Mesh Inpainting Using Self-Supervised Graph Convolutional Networks

Reference: Shota Hattori, Tatsuya Yatagawa, Yutaka Ohtake, Hiromasa Suzuki, “Learning Self-Prior for Mesh Inpainting Using Self-Supervised Graph Convolutional Networks,” IEEE Transactions on Visualization and Computer Graphics (2024).

Monte Carlo Path Tracing and Statistical Event Detection for Event Camera Simulation

graphics

rendering

Monte Carlo Path Tracing and Statistical Event Detection for Event Camera Simulation

Reference: Yuichiro Manabe, Tatsuya Yatagawa, Shigeo Morishima, Hiroyuki Kubo, “Monte Carlo Path Tracing and Statistical Event Detection for Event Camera Simulation,” (2024).

Primitive-based Model Reduction for Huge 3D Meshes of Industrial Plants

graphics

geometry

applications

Primitive-based Model Reduction for Huge 3D Meshes of Industrial Plants

Reference: Haruki Hattori, Yutaka Ohtake, Tatsuya Yatagawa, Kazutoshi Miyamoto, Masashi Hirota, “Primitive-based Model Reduction for Huge 3D Meshes of Industrial Plants,” (2024).

Learning-Based Spotlight Position Optimization for Non-Line-of-Sight Human Localization and Posture Classification

vision

deep learning

Learning-Based Spotlight Position Optimization for Non-Line-of-Sight Human Localization and Posture Classification

Reference: Sreenithy Chandran, Tatsuya Yatagawa, Hiroyuki Kubo, Suren Jayasuriya, “Learning-Based Spotlight Position Optimization for Non-Line-of-Sight Human Localization and Posture Classification,” (2024).

Sparse-View Cone-Beam CT Reconstruction by Bar-by-Bar Neural FDK Algorithm

applications

NDT

Reference: Siqi Wang, Tatsuya Yatagawa, Yutaka Ohtake, Hiromasa Suzuki, “Sparse-View Cone-Beam CT Reconstruction by Bar-by-Bar Neural FDK Algorithm,” Nondestructive Testing and Evaluation (2023).

Bin-scanning: Segmentation of X-ray CT volume of binned parts using Morse skeleton graph of distance transform

graphics

geometry

applications

Bin-scanning: Segmentation of X-ray CT volume of binned parts using Morse skeleton graph of distance transform

Reference: Yuta Yamauchi, Tatsuya Yatagawa, Yutaka Ohtake, Hiromasa Suzuki, “Bin-scanning: Segmentation of X-ray CT volume of binned parts using Morse skeleton graph of distance transform,” Computational Visual Media (2023).

Event-Based Camera Simulation Using Monte Carlo Path Tracing with Adaptive Denoising

graphics

rendering

Event-Based Camera Simulation Using Monte Carlo Path Tracing with Adaptive Denoising

Reference: Yuta Tsuji, Tatsuya Yatagawa, Hiroyuki Kubo, Shigeo Morishima, “Event-Based Camera Simulation Using Monte Carlo Path Tracing with Adaptive Denoising,” (2023).

End-to-End Deep Learning for Reconstructing Segmented 3D CT Image ffrom Multi-Energy X-ray Projections

applications

NDT

End-to-End Deep Learning for Reconstructing Segmented 3D CT Image ffrom Multi-Energy X-ray Projections

Reference: Wang Siqi, Tatsuya Yatagawa, Yutaka Ohtake, Toru Aoki, Jun Hotta, “End-to-End Deep Learning for Reconstructing Segmented 3D CT Image ffrom Multi-Energy X-ray Projections,” (2023).

Degree of local symmetry for geometry-aware selective part visualisation on CT volumes

applications

NDT

Degree of local symmetry for geometry-aware selective part visualisation on CT volumes

Reference: Nobumichi Yasunami, Tatsuya Yatagawa, Hiromasa Suzuki, Yutaka Ohtake, “Degree of local symmetry for geometry-aware selective part visualisation on CT volumes,” Nondestructive Testing and Evaluation (2022).

Image Based Measurement of Individual Fiber Lengths for Randomly Oriented Short Fiber Composites

applications

NDT

Image Based Measurement of Individual Fiber Lengths for Randomly Oriented Short Fiber Composites

Reference: Siqi Wang, Tatsuya Yatagawa, Hiromasa Suzuki, Yutaka Ohtake, “Image Based Measurement of Individual Fiber Lengths for Randomly Oriented Short Fiber Composites,” Journal of Nondestructive Evaluation (2022).

Real-time Shading with Free-form Planar Area Lights using Linearly Transformed Cosines

graphics

rendering

Real-time Shading with Free-form Planar Area Lights using Linearly Transformed Cosines

Reference: Takahiro Kuge, Tatsuya Yatagawa, Shigeo Morishima, “Real-time Shading with Free-form Planar Area Lights using Linearly Transformed Cosines,” Journal of Computer Graphics Techniques (2022).

Learning Self-prior for Mesh Denoising using Dual Graph Convolutional Networks

graphics

geometry

deep learning

Learning Self-prior for Mesh Denoising using Dual Graph Convolutional Networks

Reference: Shota Hattori, Tatsuya Yatagawa, Yutaka Ohtake, Hiromasa Suzuki, “Learning Self-prior for Mesh Denoising using Dual Graph Convolutional Networks,” (2022).

Light Source Selection in Primary-Sample-Space Photon Sampling

graphics

rendering

deep learning

Reference: Yuta Tsuji, Tatsuya Yatagawa, Shigeo Morishima, “Light Source Selection in Primary-Sample-Space Photon Sampling,” (2021).

Extended Differentiable Marching Cubes by Manifold-Preserving Shape Inflation

graphics

geometry

deep learning

Extended Differentiable Marching Cubes by Manifold-Preserving Shape Inflation

Reference: Kiichi Itoh, Tatsuya Yatagawa, Yutaka Ohtake, Hiromasa Suzuki, “Extended Differentiable Marching Cubes by Manifold-Preserving Shape Inflation,” (2021).

Deep Mesh Prior: Unsupervised Mesh Restoration using Graph Convolutional Networks

graphics

geometry

deep learning

Deep Mesh Prior: Unsupervised Mesh Restoration using Graph Convolutional Networks

Reference: Shota Hattori, Tatsuya Yatagawa, Yutaka Ohtake, Hiromasa Suzuki, “Deep Mesh Prior: Unsupervised Mesh Restoration using Graph Convolutional Networks,” (2021).

LinSSS: Linear decomposition of heterogeneous subsurface scattering for real-time screen-space rendering

graphics

rendering

Reference: Tatsuya Yatagawa, Yasushi Yamaguchi, Shigeo Morishima, “LinSSS: Linear decomposition of heterogeneous subsurface scattering for real-time screen-space rendering,” The Visual Computer (Special Issue of Computer Graphics International 2020) (2020).

Data Compression for Measured Heterogeneous Subsurface Scattering via Scattering Profile Blending

graphics

rendering

Reference: Tatsuya Yatagawa, Hideki Todo, Yasushi Yamaguchi, Shigeo Morishima, “Data Compression for Measured Heterogeneous Subsurface Scattering via Scattering Profile Blending,” The Visual Computer (2020).

Real-time rendering of layered materials with anisotorpic normal distributions

graphics

rendering

Reference: Tomoya Yamaguchi, Tatsuya Yatagawa, Yusuke Tokuyoshi, Shigeo Morishima, “Real-time rendering of layered materials with anisotorpic normal distributions,” Computational Visual Media (2020).

Real-time Indirect Illumination of Emissive Inhomogeneous Volumes using Layered Polygonal Area Lights

graphics

rendering

Real-time Indirect Illumination of Emissive Inhomogeneous Volumes using Layered Polygonal Area Lights

Reference: Takahiro Kuge, Tatsuya Yatagawa, Shigeo Morishima, “Real-time Indirect Illumination of Emissive Inhomogeneous Volumes using Layered Polygonal Area Lights,” Computer Graphics Forum (Special Issue of Pacific Graphics 2019) (2019).

FSNet: An Identity-aware Generative Model for Image-based Face Swapping

image & video

deep learning

Reference: Ryota Natsume, Tatsuya Yatagawa, Shigeo Morishima, “FSNet: An Identity-aware Generative Model for Image-based Face Swapping,” (2018).

Efficient Metropolis Path Sampling for Material Editing and Re-rendering

graphics

rendering

Reference: Tomoya Yamaguchi, Tatsuya Yatagawa, Shigeo Morishima, “Efficient Metropolis Path Sampling for Material Editing and Re-rendering,” (2018).

RSGAN: face swapping and editing via region separation in latent spaces

image & video

deep learning

Reference: Ryota Natsume, Tatsuya Yatagawa, Shigeo Morishima, “RSGAN: face swapping and editing via region separation in latent spaces,” (2018).

Hitotsubashi University
School of Social Data Science
Graphics and Vision Labratory

Projects

Projects

NeMCoF: Neural Material Composition Fields for Material Decomposition in Sparse-View Spectral X-ray CT

Towards accelerating polarization path tracing of multi-bounce Smith microfacet BSDFs

Learning Scatter Artifact Correction in Cone-Beam X-Ray CT Using Incomplete Projections with Beam Hole Array

X-ray 3D Fiber Orientation Tomography via Alternating Optimization of Scattering Coefficients and Directions

Learning Self-Prior for Mesh Inpainting Using Self-Supervised Graph Convolutional Networks

Monte Carlo Path Tracing and Statistical Event Detection for Event Camera Simulation

Primitive-based Model Reduction for Huge 3D Meshes of Industrial Plants

Learning-Based Spotlight Position Optimization for Non-Line-of-Sight Human Localization and Posture Classification

Sparse-View Cone-Beam CT Reconstruction by Bar-by-Bar Neural FDK Algorithm

Bin-scanning: Segmentation of X-ray CT volume of binned parts using Morse skeleton graph of distance transform

Event-Based Camera Simulation Using Monte Carlo Path Tracing with Adaptive Denoising

End-to-End Deep Learning for Reconstructing Segmented 3D CT Image ffrom Multi-Energy X-ray Projections

Degree of local symmetry for geometry-aware selective part visualisation on CT volumes

Image Based Measurement of Individual Fiber Lengths for Randomly Oriented Short Fiber Composites

Real-time Shading with Free-form Planar Area Lights using Linearly Transformed Cosines

Learning Self-prior for Mesh Denoising using Dual Graph Convolutional Networks

Light Source Selection in Primary-Sample-Space Photon Sampling

Extended Differentiable Marching Cubes by Manifold-Preserving Shape Inflation

Deep Mesh Prior: Unsupervised Mesh Restoration using Graph Convolutional Networks

LinSSS: Linear decomposition of heterogeneous subsurface scattering for real-time screen-space rendering

Data Compression for Measured Heterogeneous Subsurface Scattering via Scattering Profile Blending

Real-time rendering of layered materials with anisotorpic normal distributions

Real-time Indirect Illumination of Emissive Inhomogeneous Volumes using Layered Polygonal Area Lights

FSNet: An Identity-aware Generative Model for Image-based Face Swapping

Efficient Metropolis Path Sampling for Material Editing and Re-rendering

RSGAN: face swapping and editing via region separation in latent spaces

Sparse Pixel Sampling for Appearance Edit Propagation

Temporally Coherent Video Editing using an Edit Propagation Matrix

A Template-Based Completion Framework for Videos with Dynamic Backgrounds