Assistant Professor
Optical Media Interface Laboratory, Nara Institute of Science and Technology (NAIST)
Mail: fujimura.yuki at is.naist.jp
Yuki Fujimura received the PhD in informatics at Kyoto University in 2021.
His research interests include physics-based vision and machine learning.
News
2023/12: one paper was accepted to Scientific Reports.
2023/11: one paper was accepted to IJCV.
2023/08: two papers were accepted to ICCV2023 workshop.
2023/07: one paper was accepted to ICCV2023.
2023/06: one paper was accepted to SIGGRAPH2023 Posters.
Research project
Deep depth from focus/defocus with a camera model
Yuki Fujimura, Masaaki Iiyama, Takuya Funatomi, and Yasuhiro Mukaigawa: Deep Depth from Focal Stack with Defocus Model for Camera-Setting Invariance, International Journal of Computer Vision, Vol. 132, No. 6, pp. 1970-1985, 2024. [paper][code][arXiv][press release]
Analysis of organoid images
Neural implicit surface in non-line-of-sight imaging
Yuki Fujimura, Takahiro Kushida, Takuya Funatomi, and Yasuhiro Mukaigawa: NLOS-NeuS: Non-line-of-sight Neural Implicit Surface, The IEEE/CVF International Conference on Computer Vision (ICCV), pp. 10532-10541, 2023. <acceptance rate: 2160/8260=26.15%> [project page][paper][arXiv]
Deep multi-view stereo in foggy scenes
Yuki Fujimura, Motoharu Sonogashira, and Masaki Iiyama: Dehazing cost volume for deep multi-view stereo in scattering media with airlight and scattering coefficient estimation, Computer Vision and Image Understanding, Vol. 211, 103253, 2021. [paper] [code]
Yuki Fujimura, Motoharu Sonogashira, and Masaaki Iiyama: Dehazing Cost Volume for Deep Multi-view Stereo in Scattering Media: Asian Conference on Computer Vision (ACCV), 2020. <oral, acceptance rate: 63/768=8.2%> [paper] [code]
Time-of-flight in foggy scenes
Yuki Fujimura, Motoharu Sonogashira, and Masaaki Iiyama: Simultaneous Estimation of Object Region and Depth in Participating Media Using a ToF Camera, IEICE Transactions on Information and Systems, Vol. E103-D, No. 3, pp.660-673, 2020. [paper]
Photometric stereo in participating media
Yuki Fujimura, Masaaki Iiyama, Atshushi Hashimoto, and Michihiko Minoh: Photometric Stereo in Participating Media Using an Analytical Solution for Shape-Dependent Forward Scatter, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 42, No. 3, pp. 708-719, 2020. [paper]
Yuki Fujimura, Masaaki Iiyama, Atsushi Hashimoto, and Michihiko Minoh: Photometric Stereo in Participating Media Considering Shape-Dependent Forward Scatter, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.7445-7453, 2018. <oral, acceptance rate: 70/3303=2.1%> [paper]
Award
2024年3月, CVIM研究会奨励賞, 学習ベース両眼ステレオが持つ事前知識のNeRFへの導入, 情報処理学会
2023年8月, MIRUインタラクティブ発表賞, イベントカメラを用いた人物姿勢推定結果の更新によるレイテンシ補償と精度向上
2022年3月, 山下記念研究賞, 未知散乱条件下での深層学習によるMulti-view Stereo, 情報処理学会
2021年5月, CVIM研究会奨励賞, 3D Reconstruction in Scattering Media, 情報処理学会
2020年8月, MIRU学生奨励賞, Dehazing Cost Volume for Deep Multi-view Stereo in Scattering Media
2019年8月, MIRU学生奨励賞,Defogging Kinect: Simultaneous Estimation of Object Region and Depth in Foggy Scenes
2019年2月, 京都大学第13回ICTイノベーション優秀研究賞, Defogging Kinect: 散乱媒体下での物体領域と奥行きの同時推定
Grant
カメラ撮像モデルと深層学習の融合ーボケ画像からの距離推定手法における検証, 科学研究費助成事業 若手研究, 2022年4月 - 2025年3月
深層学習と物理モデルの融合によるシンプルな観測系での不均一散乱媒体の濃度分布推定, 日本学術振興会, 科学研究費助成事業 研究活動スタート支援, 2021年8月 - 2023年3月
散乱媒体下における三次元形状計測手法, 日本学術振興会 科学研究費助成事業 特別研究員奨励費, 2019年4月 - 2021年3月
Academic activities
第27回 画像の認識・理解シンポジウム (MIRU2024), プログラム副委員長, 2024年8月
情報処理学会 コンピュータビジョンとイメージメディア研究会 (CVIM), 運営委員, 2022年4月 - 2024年3月
Review
IEEE Transactions on Instrumentation & Measurement
The Visual Computer
IEICE Transactions on Information and Systems
ITE Transactions on Media Technology and Applications
ECCV 2024
ICCV 2023
ICPR 2022
ICME 2021