CVL@UOsaka

光を用いた高精細3次元イメージングの実世界応用に向けた展開 (JSPS科研費 基盤(A) 2016-2018)

カメラを用いた実世界物体の3次元形状推定はコンピュータビジョンの重要な基盤技術であると共に,ロボットの制御,計算機による物体認識,車の自動走行,製品の品質検査など,幅広い応用が期待されている.3次元形状推定においては,光を利用する光学的アプローチによって高品質な形状推定が可能になることが明らかになっている.本研究では,光学的3次元イメージング技術の高度化に取り組み,特に(a)多様な対象物体を扱えるようにする,(b)簡便なセットアップで使いやすくする,ことを目的に研究を行った.結果として,新しい3次元イメージング技術を開発し,これらの目標を達成することができた.

関連研究費

  • 2016年4月~2019年3月 JSPS科学研究費助成事業 基盤研究(A)
    「光を用いた高精細3次元イメージングの実世界応用に向けた展開」
    研究代表者:松下康之 配分総額 34,200千円

主要な発表文献

  • Junxuan Li; Antonio Robles-Kelly; Shaodi You; Yasuyuki Matsushita. Learning to Minify Photometric Stereo. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

     

  • Guanying Chen; Kai Han; Boxin Shi; Yasuyuki Matsushita; Kwan-Yee K. Wong. Self-calibrating Deep Photometric Stereo Networks. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

     

  • Asako Kanezaki; Yasuyuki Matsushita; Yoshifumi Nishida. RotationNet for Joint Object Categorization and Unsupervised Pose Estimation from Multi-view Images. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019.

     

  • Hiroaki Santo; Michael Waechter; Masaki Samejima; Yusuke Sugano; Yasuyuki Matsushita. Light Structure from Pin Motion: Simple and Accurate Point Light Calibration for Physics-based Modeling. Proceedings of European Conference on Computer Vision (ECCV), 2018.

     

  • Zhipeng Mo; Boxin Shi; Feng Lu; Sai-Kit Yeung; Yasuyuki Matsushita. Uncalibrated Photometric Stereo Under Natural Illumination. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

     

  • Wen-Yan Lin; Siying Liu; Jian-Huang Lai; Yasuyuki Matsushita. Dimensionality’s Blessing: Clustering Images by Underlying Distribution. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

     

  • Asako Kanezaki; Yasuyuki Matsushita; Yoshifumi Nishida. RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews From Unsupervised Viewpoints. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

     

  • Hiroaki Santo; Masaki Samejima; Yasuyuki Matsushita. Numerical shape-from-shading revisited. IPSJ Transactions on Computer Vision and Applications, vol. 10, no. 1, pp. 8–20, 2018.

     

  • Tatsunori Taniai; Yasuyuki Matsushita; Yoichi Sato; Takeshi Naemura. Continuous 3D Label Stereo Matching Using Local Expansion Moves. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 40, no. 11, pp. 2725-2739, 2018.

     

  • Dong Hyeon Cho; Yasuyuki Matsushita; Yu Wing Tai; In So Kweon. Semi-Calibrated Photometric Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018.

     

  • Shaodi You; Yasuyuki Matsushita; Sudipta N. Sinha; Yusuke Bou; Katsushi Ikeuchi. Multiview Rectification of Folded Documents. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 40, no. 2, pp. 505-511, 2018.

     

  • Tae-Hyun Oh; Yasuyuki Matsushita; Yu-Wing Tai; In So Kweon. Fast Randomized Singular Value Thresholding for Low-Rank Optimization. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 40, no. 2, pp. 376-391, 2018.

     

  • Jiawang Bian; Yasuyuki Matsushita; Sai-Tan Ming. GMS: Grid-Based Motion Statistics for Fast, Ultra-Robust Feature Correspondence. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.

     

  • Kenichiro Tanaka; Yasuhiro Mukaigawa; Takuya Funatomi; Hiroyuki Kubo; Yasuyuki Matsushita; Yasushi Yagi. Material Classification Using Frequency-and Depth-Dependent Time-of-Flight Distortion. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.

     

  • Zhipeng Mo; Boxin Shi; Yasuyuki Matsushita. Radiometric Calibration for Internet Photo Collections. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.

     

  • Kenichiro Tanaka; Yasuhiro Mukaigawa; Hiroyuki Kubo; Yasuyuki Matsushita; Yasushi Yagi. Recovering Inner Slices of Layered Translucent Objects by Multi-Frequency Illumination. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 39, no. 4, pp. 746–757, 2017.

     

  • Jaesik Park; Sudipta N Sinha; Yasuyuki Matsushita; In So Kweon. Robust Multiview Photometric Stereo Using Planar Mesh Parameterization. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 39, no. 8, pp. 1591–1604, 2017.

↑ PAGE TOP
CVL@UOsaka