Search Results for author: Ryo Furukawa

Found 13 papers, 0 papers with code

Optimizing Implicit Neural Representations from Point Clouds via Energy-Based Models

no code implementations5 Nov 2023 Ryutaro Yamauchi, Jinya Sakurai, Ryo Furukawa, Tatsushi Matsubayashi

Reconstructing a continuous surface from an unoritented 3D point cloud is a fundamental task in 3D shape processing.

Surface Reconstruction

Generalization of pixel-wise phase estimation by CNN and improvement of phase-unwrapping by MRF optimization for one-shot 3D scan

no code implementations26 Sep 2023 Hiroto Harada, Michihiro Mikamo, Ryo Furukawa, Ryushuke Sagawa, Hiroshi Kawasaki

To solve the problems, we propose a pixel-wise interpolation technique for one-shot scan, which is applicable to any types of static pattern if the pattern is regular and periodic.

Data Augmentation

Heterogeneous Domain Adaptation with Positive and Unlabeled Data

no code implementations17 Apr 2023 Junki Mori, Ryo Furukawa, Isamu Teranishi, Jun Sakuma

To overcome this issue, we propose a novel method, predictive adversarial domain adaptation (PADA), which can predict likely positive examples from the unlabeled target data and simultaneously align the feature spaces to reduce the distribution divergence between the whole source data and the likely positive target data.

Unsupervised Domain Adaptation

Continual Horizontal Federated Learning for Heterogeneous Data

no code implementations4 Mar 2022 Junki Mori, Isamu Teranishi, Ryo Furukawa

Federated learning is a promising machine learning technique that enables multiple clients to collaboratively build a model without revealing the raw data to each other.

Continual Learning Federated Learning

A Method For Adding Motion-Blur on Arbitrary Objects By using Auto-Segmentation and Color Compensation Techniques

no code implementations22 Sep 2021 Michihiro Mikamo, Ryo Furukawa, Hiroshi Kawasaki

Such a blur is sometimes considered as just a noise, however, it sometimes gives an important effect to add dynamism in the scene for photographs or videos.

CNN based dense underwater 3D scene reconstruction by transfer learning using bubble database

no code implementations21 Nov 2018 Kazuto Ichimaru, Ryo Furukawa, Hiroshi Kawasaki

Passive stereo is a simple solution for capturing dynamic scenes at underwater environment, however the shape with textureless surfaces or irregular reflections cannot be recovered.

3D Scene Reconstruction Transfer Learning +1

Multi-scale CNN stereo and pattern removal technique for underwater active stereo system

no code implementations25 Aug 2018 Kazuto Ichimaru, Ryo Furukawa, Hiroshi Kawasaki

Passive stereo is applicable to capture dynamic scenes, however the shape with textureless surfaces or irregular reflections cannot be recovered by the technique.

Stereo Matching Stereo Matching Hand

Depth estimation using structured light flow -- analysis of projected pattern flow on an object's surface --

no code implementations ICCV 2017 Ryo Furukawa, Ryusuke Sagawa, Hiroshi Kawasaki

Analysis reveals that minimum two light flows, which are retrieved from two projected patterns on the object, are required for depth estimation.

Depth Estimation

Depth Estimation Using Structured Light Flow -- Analysis of Projected Pattern Flow on an Object's Surface

no code implementations ICCV 2017 Ryo Furukawa, Ryusuke Sagawa, Hiroshi Kawasaki

Analysis reveals that minimum two light flows, which are retrieved from two projected patterns on the object, are required for depth estimation.

Depth Estimation

Simultaneous independent image display technique on multiple 3D objects

no code implementations10 Sep 2016 Takuto Hirukawa, Marco Visentini-Scarzanella, Hiroshi Kawasaki, Ryo Furukawa, Shinsaku Hiura

The system, despite consisting of conventional passive LCD projectors, is able to project different images and patterns depending on the spatial location of the object.

Colorization Object

Active One-Shot Scan for Wide Depth Range Using a Light Field Projector Based on Coded Aperture

no code implementations ICCV 2015 Hiroshi Kawasaki, Satoshi Ono, Yuki Horita, Yuki Shiba, Ryo Furukawa, Shinsaku Hiura

The central projection model commonly used to model cameras as well as projectors, results in similar advantages and disadvantages in both types of system.

Cannot find the paper you are looking for? You can Submit a new open access paper.