Updated on 2026/06/16

写真a

 
LIU XINPENG
 
Organization
School of Computing Assistant Professor
Title
Assistant Professor
External link

Research Interests

  • Embodied Intelligence

  • Agent

  • コンピュータビジョン

  • コンピュータグラフィックス

  • 3次元復元

Research Areas

  • Informatics / Perceptual information processing

  • Environmental Science/Agriculture Science / Agricultural environmental engineering and agricultural information engineering

Education

  • Osaka University   Graduate School of Information Science and Technology   Department of Multimedia Engineering

    2021.10 - 2025.12

    　 More details

  • Osaka University   Graduate School of Engineering

    2019.4 - 2021.3

    　 More details

Research History

  • Institute of Science Tokyo   Assistant Professor

    2026.4

    　 More details

  • Osaka University   Graduate School of Information Science and Technology   Specially Appointed Junior Associate Professor

    2026.1 - 2026.3

    　 More details

Papers

  • NRGS: Neural Regularization for Robust 3D Semantic Gaussian Splatting Reviewed

    Zaiyan Yang, Xinpeng Liu, Heng Guo, Jinglei Shi, Zhanyu Ma, Fumio Okura

    IEEE International Conference on Multimedia and Expo (ICME'26)   2026.7

    　More details

    Language：English   Publishing type：Research paper (international conference proceedings)  

    researchmap

  • PlantPose: Universal Plant Skeleton Estimation via Tree-constrained Graph Generation

    Xinpeng Liu, Hiroaki Santo, Yosuke Toda, Fumio Okura

    International Journal of Computer Vision   2026.6

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    <jats:title>Abstract</jats:title>
    <jats:p>
    Accurate estimation of plant skeletal structures (
    <jats:italic>e.g.</jats:italic>
    , branching structures) from images is essential for smart agriculture and plant science. Unlike human skeletons with fixed topology, plant skeleton estimation presents a unique challenge,
    <jats:italic>i.e.</jats:italic>
    , estimating arbitrary tree graphs from images. To address this problem, we introduce
    <jats:bold>PlantPose</jats:bold>
    , a universal plant skeleton estimator via tree-constrained graph generation. PlantPose combines learning-based graph generation with traditional graph algorithms to enforce tree constraints during the training loop. To enhance the model’s generalization capability, we curate a large and diverse dataset comprising real-world and synthetic plant images, along with simplified representations (
    <jats:italic>e.g.</jats:italic>
    , sketches and abstract drawings). This dataset enables the generalized model to adapt to diverse input styles and categories of plant images while preserving topological consistency. Our approach demonstrates robust and accurate plant skeleton estimation across multiple domains, including previously unseen out-of-domain scenarios. Further analyses highlight the method’s strengths and limitations in handling complex, heterogeneous data distributions. All implementations and datasets are available at
    <jats:ext-link xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="https://github.com/huntorochi/PlantPose/" ext-link-type="uri">https://github.com/huntorochi/PlantPose/</jats:ext-link>
    .
    </jats:p>

    DOI： 10.1007/s11263-026-02882-4

    researchmap

  • Gaussian Mesh Renderer for Lightweight Differentiable Rendering Reviewed

    2026.5

    　More details

    Language：English   Publishing type：Research paper (international conference proceedings)  

    researchmap

  • Zero-shot Hierarchical Plant Segmentation via Foundation Segmentation Models and Text-to-image Attention Reviewed

    Xing, Junhao, Miyakawa, Ryohei, Yang, Yang, Liu, Xinpeng, Shinoda, Risa, Santo, Hiroaki, Toda, Yosuke, Okura, Fumio

    Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV'26)   2026.3

    　More details

    Language：English   Publishing type：Research paper (international conference proceedings)  

    researchmap

  • Masks-to-Skeleton: Multi-View Mask-Based Tree Skeleton Extraction with 3D Gaussian Splatting Reviewed

    Xinpeng Liu, Kanyu Xu, Risa Shinoda, Hiroaki Santo, Fumio Okura

    Sensors   2025.7

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    DOI： 10.3390/s25144354

    researchmap

  • LeafGen: Structure-aware Leaf Image Generation for Annotation-free Leaf Instance Segmentation Reviewed

    Naoki Asada, Xinpeng Liu, Kanyu Xu, Ryohei Miyakawa, Yang Yang, Hiroaki Santo, Yosuke Toda, Fumio Okura

    Plant Phenomics   7 ( 4 )   100092 - 100092   2025

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    DOI： 10.1016/j.plaphe.2025.100092

    researchmap

  • HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting Reviewed

    Xinpeng Liu, Zeyi Huang, Fumio Okura, Yasuyuki Matsushita

    2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)   2025

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    researchmap

  • TreeFormer: Single-View Plant Skeleton Estimation via Tree-Constrained Graph Generation Reviewed

    Xinpeng Liu, Hiroaki Santo, Yosuke Toda, Fumio Okura

    2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)   2024

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    researchmap

▼display all

Presentations

  • HoGS: Unified near and far object reconstruction via homogeneous gaussian splatting Invited

    Xinpeng Liu, Zeyi Huang, Fumio Okura, Yasuyuki Matsushita

    第28回 画像の認識・理解シンポジウム（MIRU2025）  2025.7 

    　More details

    Presentation type：Oral presentation (invited, special)  

    researchmap

  • PlantPose: Plant Skeleton Estimation in 2D and 3D Invited

    Xinpeng Liu

    Machine Learning for Cyber-Agricultural Systems (MLCAS)  2025.6 

    　More details

    Presentation type：Oral presentation (invited, special)  

    researchmap

Awards

  • 京都リサーチパーク賞

    2022.6   KYOTO大学生グローバルベンチャーコンテスト2022  

    　More details

Teaching Experience

  • Computer Logic Design

    2026.4 Institution：Institute of Science Tokyo

    　More details