Papers - Isogawa, Mariko

Listening Human Behavior: 3D Human Pose Estimation With Acoustic Signals

Y Shibata, Y Kawashima, M Isogawa, G Irie, A Kimura, Y Aoki

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  2023

Research paper (international conference proceedings), Accepted

Importance ranking estimation of objects in a city scene

Y Nitta, M Isogawa, R Yonetani, M Sugimoto

IEICE Technical Report; IEICE Tech. Rep. 122 (367), 43-48  2023

Importance Rank-Learning of Objects in Urban Scenes for Assisting Visually Impaired People

Y Nitta, M Isogawa, R Yonetani, M Sugimoto

IEEE Access  2023

Research paper (scientific journal), Accepted

疎な計測情報に基づくシーン状態推定の展望 [塾内限定]

M Isogawa

慶應義塾大学 理工学部  2023

Research paper (other academic)

Video and audio presentation device, video and audio presentation method, and program

M Isogawa, D Mikami, K Takahashi, Y Kusachi

US Patent 11,715,240  2023

Silhouette-Based 3D Human Pose Estimation Using a Single Wrist-Mounted 360° Camera.

Ryosuke Hori, Ryo Hachiuma, Mariko Isogawa, Dan Mikami, Hideo Saito

IEEE Access 10   54957 - 54968 2022

Research paper (scientific journal),  ISSN  2169-3536

• Access to Document (DOI)

Bilateral video magnification filter

S Takeda, K Niwa, M Isogawa, S Shimizu, K Okami, Y Aono

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …  2022

Learning data generation device, learning data generation method, and program

D Mikami, M Isogawa, H Yabushita, Y Kusachi

US Patent App. 17/620,608  2022

Information completion apparatus, method and program

M Isogawa, D Mikami, K Takahashi, Y Kusachi

US Patent App. 17/613,464  2022

Coordinate system conversion parameter estimating apparatus, method and program

K Takahashi, D Mikami, M Isogawa, Y Kusachi

US Patent App. 17/435,759  2022

Rotation state estimation device, method and program

D Mikami, M Isogawa, K Takahashi, Y Kusachi

US Patent App. 17/438,867  2022

Virtual environment construction apparatus, video presentation apparatus, model learning apparatus, optimal depth decision apparatus, methods for the same, and program

K Takahashi, D Mikami, M Isogawa, A Kojima, H Kimata, A Matsumoto

US Patent App. 17/845,010  2022

Virtual environment construction apparatus, video presentation apparatus, model learning apparatus, optimal depth decision apparatus, methods for the same, and program

K Takahashi, D Mikami, M Isogawa, A Kojima, H Kimata, A Matsumoto

US Patent 11,395,947  2022

Video synchronization device, video synchronization method, and program

SUN Siqi, K Takahashi, D Mikami, M Isogawa, Y Kusachi

US Patent App. 17/442,077  2022

Training data generation apparatus, method and program

M Isogawa, D Mikami, K Takahashi, Y Kusachi

US Patent App. 17/429,547  2022

Motion classification model learning apparatus, motion classification apparatus, motion classification model learning method and program

M Isogawa, D Mikami, K Takahashi, H Kimata, A Matsumoto

US Patent App. 17/059,121  2021

Silhouette-based synthetic data generation for 3D human pose estimation with a single wrist-mounted 360° camera

R Hori, R Hachiuma, H Saito, M Isogawa, D Mikami

2021 IEEE International Conference on Image Processing (ICIP), 1304-1308    1304 - 1308 2021

• Access to Document (DOI)

Multi-view video synchronization using motion rhythms of human joints

S Sun, K Takahashi, D Mikami, M Isogawa, Y Kusachi

ITE Transactions on Media Technology and Applications 8 (2), 100-110  2020

Research paper (scientific journal)

Prodebnet: projector deblurring using a convolutional neural network

Y Kageyama, M Isogawa, D Iwai, K Sato

Optics Express 28 (14), 20391-20403 28 ( 14 ) 20391 - 20403 2020

Research paper (scientific journal)

　View Summary

Projection blur can occur in practical use cases that have non-planar and/or multi-projection display surfaces with various scattering characteristics because the surface often causes defocus and subsurface scattering. To address this issue, we propose ProDebNet, an end-to-end real-time projection deblurring network that synthesizes a projection image to minimize projection blur. The proposed method generates a projection image without explicitly estimating any geometry or scattering characteristics of the projection screen, which makes real-time processing possible. In addition, ProDebNet does not require real captured images for training data; we design a "pseudo-projected" synthetic dataset that is well-generalized to real-world blur data. Experimental results demonstrate that the proposed ProDebNet compensates for two dominant types of projection blur, i.e., defocus blur and subsurface blur, significantly faster than the baseline method, even in a real-projection scene.

• Access to Document (DOI)

Optical Non-Line-of-Sight Physics-Based 3D Human Pose Estimation.

Mariko Isogawa, Ye Yuan 0007, Matthew O'Toole, Kris M. Kitani

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR) (Computer Vision Foundation / IEEE)     7011 - 7020 2020

• Access to Document (DOI)