Masato Ishii

石井 雅人 ・ ソニーグループ株式会社

prof_pic.jpg

E-mail: masato0713 [at] gmail [dot] com

X (Twitter) · LinkedIn

English · 日本語

石井 雅人（Masato Ishii）
所属：ソニーグループ株式会社
研究分野：音・動画生成、拡散モデル一般

経歴

  • 2019 – 現在：ソニーグループ株式会社
    • 株式会社ソニーリサーチ（出向：2023 – 2026）
  • 2017 – 2019：理研AIP（兼務：客員研究員）
  • 2010 – 2019：NEC
  • 博士（電子情報学）：東京大学大学院 情報理工学系研究科（指導教員：杉山将）

最近発表した主な論文

全リストは Google Scholar をご覧ください。

  1. NeurIPS
    Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video Diffusion
    Zhengyang Yu, Akio Hayakawa, Masato Ishii, Qingtao Yu, Xuesong Li, Takashi Shibuya, Yuki Mitsufuji, and Jing Zhang
    In Advances in Neural Information Processing Systems (NeurIPS), 2026
  2. ACCV
    Pose Mutation: Target-Pose-Free Consistent Pose Exploration for Portrait Generation
    Masaru Mizuochi, Takashi Shibuya, Masato Ishii, and Vali Lalioti
    In Asian Conference on Computer Vision (ACCV), 2026
  3. ECCV
    spa.png
    Spectral Prior for Reducing Exposure Bias in Diffusion Models
    Yuya Kobayashi, Masato Ishii, Yuta Takida, Takashi Shibuya, and Yuki Mitsufuji
    In European Conference on Computer Vision (ECCV), 2026
    arXiv Code
  4. ECCV
    sbsv2a.png
    Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance
    Akio Hayakawa, Masato Ishii, Takashi Shibuya, and Yuki Mitsufuji
    In European Conference on Computer Vision (ECCV), 2026
    arXiv Website
  5. CVPR
    echoes_over_time.png
    Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models
    Christian Simon, Masato Ishii, Wei-Yao Wang, Koichi Saito, Akio Hayakawa, Dongseok Shim, Zhi Zhong, Shuyang Cui, Takashi Shibuya, Shusuke Takahashi, and Yuki Mitsufuji
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
    arXiv Website
  6. IJCNN
    svg_baseline.png
    A Simple but Strong Baseline for Sounding Video Generation: Effective Adaptation of Audio and Video Diffusion Models for Joint Generation
    Masato Ishii, Akio Hayakawa, Takashi Shibuya, and Yuki Mitsufuji
    In International Joint Conference on Neural Networks (IJCNN), 2025
    arXiv Code
  7. ICCV
    titan_guide.png
    Titan-Guide: Taming Inference-Time Alignment for Guided Text-to-Video Diffusion Models
    Christian Simon, Masato Ishii, Akio Hayakawa, Zhi Zhong, Shusuke Takahashi, Takashi Shibuya, and Yuki Mitsufuji
    In IEEE/CVF International Conference on Computer Vision (ICCV), 2025
    arXiv Code Website
  8. ICLR
    continual_personalization.png
    Mining Your Own Secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models
    Saurav Jha, Shiqi Yang, Masato Ishii, Mengjie Zhao, Muhammad Jehanzeb Mirza, Dong Gong, Lina Yao, Shusuke Takahashi, and Yuki Mitsufuji
    In International Conference on Learning Representations (ICLR), 2025
    arXiv Website
  9. ICLR
    mmdisco.png
    MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation
    Akio Hayakawa, Masato Ishii, Takashi Shibuya, and Yuki Mitsufuji
    In International Conference on Learning Representations (ICLR), 2025
    arXiv Code
  10. CVPR
    mmaudio.png
    MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
    Ho Kei Cheng, Masato Ishii, Akio Hayakawa, Takashi Shibuya, Alexander Schwing, and Yuki Mitsufuji
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
    arXiv Code Website

招待講演・寄稿

受賞

国際・国内会議などの運営

  • Workshop organizer: Gen4AVC (ICCV 2025, ECCV 2026)
  • 画像の認識・理解シンポジウム（MIRU）：運営委員長（2025-2026）、財務委員長（2018）
  • 電子情報通信学会 PRMU研究会：副委員長（2025-2026）、幹事（2017-2018）、専門委員（2016, 2019-2022）
  • International Conference on Machine Vision Applications（MVA）：publicity chair (2019), organizing committee (2015, 2017)