2023/12/26 更新

カワハラ リョウ
川原 僚
KAWAHARA Ryou
Scopus 論文情報  
総論文数: 0  総Citation: 0  h-index: 7

Citation Countは当該年に発表した論文の被引用数

職名
助教
外部リンク

研究キーワード

  • コンピュータビジョン

取得学位

  • 京都大学  -  博士(情報学)   2019年03月

学内職務経歴

  • 2021年04月 - 現在   九州工業大学   大学院情報工学研究院   知能情報工学研究系     助教

所属学会・委員会

  • 2021年07月 - 現在   IEEE   アメリカ合衆国

  • 2020年05月 - 現在   情報処理学会   日本国

論文

  • Teleidoscopic Imaging System for Microscale 3D Shape Reconstruction 査読有り

    Ryo Kawahara, Meng-Yu Jennifer Kuo, and Shohei Nobuhara

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)   2023年11月

     詳細を見る

    担当区分:筆頭著者   記述言語:英語   掲載種別:研究論文(国際会議プロシーディングス)

  • Light Source Separation and Intrinsic Image Decomposition Under AC Illumination 査読有り

    Yusaku Yoshida, Ryo Kawahara, and Takahiro Okabe

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),   2023年11月

     詳細を見る

    記述言語:英語   掲載種別:研究論文(国際会議プロシーディングス)

  • Polarimetric Underwater Stereo 査読有り

    Ryo Kawahara, Meng-Yu Jennifer Kuo, Takahiro Okabe

    Image Analysis: 22nd Scandinavian Conference, SCIA 2023, Kittilä, Finland, April 18–21, 2023, Proceedings 22. Springer International Publishing ( Springer )   2023年04月

     詳細を見る

    担当区分:筆頭著者   記述言語:英語   掲載種別:研究論文(国際会議プロシーディングス)

  • Separating Partially Polarized Diffuse and Specular Reflection Components Under Unpolarized Light Sources(共著) 査読有り

    Soma Kajiyama, Taihe Piao, Ryo Kawahara, Takahiro Okabe

    Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023   2023年01月

     詳細を見る

    記述言語:英語   掲載種別:研究論文(国際会議プロシーディングス)

  • Online Illumination Planning for Shadow-Robust Photometric Stereo(共著) 査読有り

    Hirochika Tanikawa, Ryo Kawahara, and Takahiro Okabe

    Frontiers of Computer Vision 28th International Workshop, IW-FCV 2022, Hiroshima, Japan, February 21–22, 2022, Revised Selected Papers ( Springer Cham )   2022年02月

     詳細を見る

    記述言語:英語   掲載種別:研究論文(国際会議プロシーディングス)

    Photometric stereo is a technique for estimating normals of an object surface from its images taken under different light source directions. In general, photometric stereo suffers from shadows, because almost no information on surface normals is available from shadowed pixels. In this paper, we propose an illumination planning for shadow-robust Lambertian photometric stereo; it optimizes the light source directions adaptively for an object of interest, because cast shadows depend on the entire shape of the object. More specifically, our proposed method iteratively adds the optimal light source for surface normal estimation by taking the visibility and linear independence of light source directions into consideration on the basis of the previously captured images of the object. We implemented our illumination planning with a programmable light source in an online manner, and achieve shadow-robust surface normal estimation from a small number of images.

  • Spectral Absorption from Two-view Hyperspectral Images(共著) 査読有り

    Kenta Kageyama, Ryo Kawahara, Takahiro Okabe

    Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications ( Science and Technology Publications )   4   715 - 721   2022年02月

     詳細を見る

    記述言語:英語   掲載種別:研究論文(国際会議プロシーディングス)

    Online   Online   2022年02月06日  -  2022年02月08日

    When light passes through a liquid, its energy is attenuated due to absorption. The attenuation depends both on the spectral absorption coefficient of a liquid and on the optical path length of light, and is described by the Lambert-Beer law. The spectral absorption coefficients of liquids are often unknown in real-world applications and to be measured/estimated in advance, because they depend not only on liquid media themselves but also on dissolved materials. In this paper, we propose a method for estimating the spectral absorption coefficient of a liquid only from two-view hyperspectral images of an under-liquid scene taken from the outside of the liquid in a passive and non-contact manner. Specifically, we show that the estimation results in Non-negative Matrix Factorization (NMF) because both the objective variables and the explanatory variables are all nonnegative, and then study the ambiguity in matrix factorization. We conducted a number of experiments using real hyperspectral images, and confirmed that our method works well and is useful for reconstructing shape of an under-liquid scene.

    DOI: 10.5220/0010917600003124

    DOI: 10.5220/0010917600003124

    その他リンク: https://www.scitepress.org/PublicationsDetail.aspx?ID=Uh/LNB8M8A8=&t=1

  • Surface Normals and Shape From Water(共著) 査読有り 国際誌

    M. J. Kuo, S. Murai, R. Kawahara, S. Nobuhara, K. Nishino

    IEEE Transactions on Pattern Analysis and Machine Intelligence ( IEEE ComputerSociety )   44 ( 12 )   9150 - 9162   Early Access   2021年10月

     詳細を見る

    記述言語:英語   掲載種別:研究論文(学術雑誌)

    In this paper, we introduce a novel method for reconstructing surface normals and depth of dynamic objects in water. Past shape recovery methods have leveraged various visual cues for estimating shape (e.g., depth) or surface normals. Methods that estimate both compute one from the other. We show that these two geometric surface properties can be simultaneously recovered for each pixel when the object is observed underwater. Our key idea is to leverage multi-wavelength near-infrared light absorption along different underwater light paths in conjunction with surface shading. Our method can handle both Lambertian and non-Lambertian surfaces. We derive a principled theory for this surface normals and shape from water method and a practical calibration method for determining its imaging parameters values. By construction, the method can be implemented as a one-shot imaging system. We prototype both an off-line and a video-rate imaging system and demonstrate the effectiveness of the method on a number of real-world static and dynamic objects. The results show that the method can recover intricate surface features that are otherwise inaccessible.

    DOI: 10.1109/TPAMI.2021.3121963

    Scopus

    PubMed

    その他リンク: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85141892850&origin=inward

  • Non-Rigid Shape from Water 査読有り 国際誌

    Kuo M.Y.J., Kawahara R., Nobuhara S., Nishino K.

    IEEE Transactions on Pattern Analysis and Machine Intelligence   43 ( 7 )   2220 - 2232   2021年07月

     詳細を見る

    担当区分:責任著者   記述言語:英語   掲載種別:研究論文(学術雑誌)

    We introduce a novel 3D sensing method for recovering a consistent, dense 3D shape of a dynamic, non-rigid object in water. The method reconstructs a complete (or fuller) 3D surface of the target object in a canonical frame (e.g., rest shape) as it freely deforms and moves between frames by estimating underwater 3D scene flow and using it to integrate per-frame depth estimates recovered from two near-infrared observations. The reconstructed shape is refined in the course of this global non-rigid shape recovery by leveraging both geometric and radiometric constraints. We implement our method with a single camera and a light source without the orthographic assumption on either by deriving a practical calibration method that estimates the point source position with respect to the camera. Our reconstruction method also accounts for scattering by water. We prototype a video-rate imaging system and show 3D shape reconstruction results on a number of real-world static, deformable, and dynamic objects and creatures in real-world water. The results demonstrate the effectiveness of the method in recovering complete shapes of complex, non-rigid objects in water, which opens new avenues of application for underwater 3D sensing in the sub-meter range.

    DOI: 10.1109/TPAMI.2021.3075450

    Scopus

    その他リンク: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85105096247&origin=inward

  • Shape from sky: Polarimetric normal recovery under the sky 査読有り

    Ichikawa T., Purri M., Kawahara R., Nobuhara S., Dana K., Nishino K.

    Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition   14827 - 14836   2021年01月

     詳細を見る

    担当区分:責任著者   記述言語:英語   掲載種別:研究論文(国際会議プロシーディングス)

    The sky exhibits a unique spatial polarization pattern by scattering the unpolarized sun light. Just like insects use this unique angular pattern to navigate, we use it to map pixels to directions on the sky. That is, we show that the unique polarization pattern encoded in the polarimetric appearance of an object captured under the sky can be decoded to reveal the surface normal at each pixel. We derive a polarimetric reflection model of a diffuse plus mirror surface lit by the sun and a clear sky. This model is used to recover the per-pixel surface normal of an object from a single polarimetric image or from multiple polarimetric images captured under the sky at different times of the day. We experimentally evaluate the accuracy of our shape-from-sky method on a number of real objects of different surface compositions. The results clearly show that this passive approach to fine-geometry recovery that fully leverages the unique illumination made by nature is a viable option for 3D sensing. With the advent of quad-Bayer polarization chips, we believe the implications of our method span a wide range of domains.

    DOI: 10.1109/CVPR46437.2021.01459

    Scopus

    その他リンク: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85117320663&origin=inward

  • Polarimetric Normal Stereo 査読有り

    Fukao Y., Kawahara R., Nobuhara S., Nishino K.

    Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition   682 - 690   2021年01月

     詳細を見る

    担当区分:責任著者   記述言語:英語   掲載種別:研究論文(国際会議プロシーディングス)

    We introduce a novel method for recovering per-pixel surface normals from a pair of polarization cameras. Unlike past methods that use polarimetric observations as auxiliary features for correspondence matching, we fully integrate them in cost volume construction and filtering to directly recover per-pixel surface normals, not as byproducts of recovered disparities. Our key idea is to introduce a polarimetric cost volume of distance defined on the polarimetric observations and the polarization state computed from the surface normal. We adapt a belief propagation algorithm to filter this cost volume. The filtering algorithm simultaneously estimates the disparities and surface normals as separate entities, while effectively denoising the original noisy polarimetric observations of a quad-Bayer polarization camera. In addition, in contrast to past methods, we model polarimetric light reflection of mesoscopic surface roughness, which is essential to account for its illumination-dependency. We demonstrate the effectiveness of our method on a number of complex, real objects. Our method offers a simple and detailed 3D sensing capability for complex, non-Lambertian surfaces.

    DOI: 10.1109/CVPR46437.2021.00074

    Scopus

    その他リンク: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85121792626&origin=inward

  • Appearance and shape from water reflection 査読有り

    Kawahara R., Kuo M.Y.J., Nobuhara S., Nishino K.

    Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020   128 - 136   2020年03月

     詳細を見る

    担当区分:筆頭著者   記述言語:英語   掲載種別:研究論文(国際会議プロシーディングス)

    This paper introduces single-image geometric and appearance reconstruction from water reflection photography, i.e., images capturing direct and water-reflected real-world scenes. Water reflection offers an additional viewpoint to the direct sight, collectively forming a stereo pair. The water-reflected scene, however, includes internally scattered and reflected environmental illumination in addition to the scene radiance, which precludes direct stereo matching. We derive a principled iterative method that disentangles this scene radiometry and geometry for reconstructing 3D scene structure as well as its high-dynamic range appearance. In the presence of waves, we simultaneously recover the wave geometry as surface normal perturbations of the water surface. Most important, we show that the water reflection enables calibration of the camera. In other words, for the first time, we show that capturing a direct and water-reflected scene in a single exposure forms a self-calibrating HDR catadioptric stereo camera. We demonstrate our method on a number of images taken in the wild. The results demonstrate a new means for leveraging this accidental catadioptric camera.

    DOI: 10.1109/WACV45572.2020.9093268

    Scopus

    その他リンク: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85085485176&origin=inward

  • Surface normals and shape from water 査読有り

    Murai S., Kuo M.Y., Kawahara R., Nobuhara S., Nishino K.

    Proceedings of the IEEE International Conference on Computer Vision   2019-October   7829 - 7837   2019年10月

     詳細を見る

    担当区分:責任著者   記述言語:英語   掲載種別:研究論文(国際会議プロシーディングス)

    In this paper, we introduce a novel method for reconstructing surface normals and depth of dynamic objects in water. Past shape recovery methods have leveraged various visual cues for estimating shape (e.g., depth) or surface normals. Methods that estimate both compute one from the other. We show that these two geometric surface properties can be simultaneously recovered for each pixel when the object is observed underwater. Our key idea is to leverage multi-wavelength near-infrared light absorption along different underwater light paths in conjunction with surface shading. We derive a principled theory for this surface normals and shape from water method and a practical calibration method for determining its imaging parameters values. By construction, the method can be implemented as a one-shot imaging system. We prototype both an off-line and a video-rate imaging system and demonstrate the effectiveness of the method on a number of real-world static and dynamic objects. The results show that the method can recover intricate surface features that are otherwise inaccessible.

    DOI: 10.1109/ICCV.2019.00792

    Scopus

    その他リンク: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85081900261&origin=inward

  • Dynamic 3D capture of swimming fish by underwater active stereo 査読有り

    Kawahara R., Nobuhara S., Matsuyama T.

    Methods in Oceanography   17   118 - 137   2016年12月

     詳細を見る

    担当区分:筆頭著者   記述言語:英語   掲載種別:研究論文(学術雑誌)

    This paper presents an underwater active stereo system that realizes 3D capture of dynamic objects in water such as swimming fish. The key idea on realizing a practical underwater 3D sensing is to model the refraction process by our pixel-wise varifocal camera model that provides efficient forward (3D to 2D) projections as well as an underwater projector–camera calibration. Evaluations demonstrate that our method achieves reasonable calibration accuracy using off-the-shelf cameras and projectors, and provides a 3D capture of real swimming fish in water.

    DOI: 10.1016/j.mio.2016.08.002

    Scopus

    その他リンク: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84988346673&origin=inward

  • Interference-Free Epipole-Centered Structured Light Pattern for Mirror-Based Multi-view Active Stereo 査読有り

    Tahara T., Kawahara R., Nobuhara S., Matsuyama T.

    Proceedings - 2015 International Conference on 3D Vision, 3DV 2015   153 - 161   2015年11月

     詳細を見る

    担当区分:責任著者   記述言語:英語   掲載種別:研究論文(国際会議プロシーディングス)

    This paper is aimed at proposing a new structured light pattern for mirror-based multi-view active stereo so that the patterns cast onto the object surface do not interfere even where the object is illuminated by the projector directly and indirectly via mirror. The key idea of our interference-free projection is to encode the projector pixel locations so that they do not collide with the code from other projector pixels by exploiting the epipolar geometry defined by the real and the virtual projectors. We prove that our new encoding does not generate code collisions between the direct and indirect patterns from the real and the virtual projectors respectively. Evaluations using real and synthesized datasets demonstrate that our approach can realize an interference-free projection without using specialized equipment such as orthographic projectors used in the state-of-the-art methods.

    DOI: 10.1109/3DV.2015.25

    Scopus

    その他リンク: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84961760444&origin=inward

▼全件表示

学術関係受賞

  • Best Paper Award

    The 28th International Workshop on Frontiers of Computer Visio   Online Illumination Planning for Shadow-Robust Photometric Stereo   2022年02月22日

    Hirochika Tanikawa, Ryo Kawahara, and Takahiro Okabe

     詳細を見る

    受賞国:日本国

  • Best presentation award

    The 28th International Workshop on Frontiers of Computer Visio   Online Illumination Planning for Shadow-Robust Photometric Stereo   2022年02月22日

    Hirochika Tanikawa, Ryo Kawahara, and Takahiro Okabe

     詳細を見る

    受賞国:日本国

担当授業科目(学内)

  • 2022年度   コンピュータビジョンA

  • 2022年度   情報工学基礎実験

  • 2021年度   知能情報工学実験演習Ⅰ

     詳細を見る

    科目区分:学部専門科目

  • 2021年度   知能情報工学プロジェクト

     詳細を見る

    科目区分:学部専門科目

教育活動に関する受賞・指導学生の受賞など

  • 学生奨励賞

    情報処理学会 第85回全国大会   偏光と陰に基づくワンショット法線推定  

    2023年03月23日

    吉田 百花

  • 学生奨励賞

    情報処理学会 第85回全国大会   ライトトランスポート獲得のための符号化照明と復号処理の同時最適化  

    2023年03月23日

    山田 悠稀

  • 学生奨励賞

    情報処理学会 第84回全国大会   再照明のための照明環境と画像補間の同時最適化  

    2022年03月

    平尾 寿希

  • 学生奨励賞

    情報処理学会 第84回全国大会   直接・大域成分の分離のための投影パタンと画像分解の同時最適化  

    2022年03月

    上田 宇起

学会・委員会等活動

  • 第24回 画像の認識・理解シンポジウム(MIRU2021)   評価委員  

    2021年03月 - 2021年04月

     詳細を見る

    MIRU論文評価功労賞を受賞

  • ICCV2023   Reviewer  

    2023年04月 - 2023年06月

  • 第26回 画像の認識・理解シンポジウム(MIRU2023)   評価委員  

    2023年03月 - 2023年05月

  • CVPR2023   Reviewer  

    2022年12月 - 2023年02月

  • 第25回 画像の認識・理解シンポジウム(MIRU2022)   評価委員  

    2022年03月 - 2022年04月