TR2025-154

Radar-Conditioned 3D Bounding Box Diffusion for Indoor Human Perception

    •  Yataka, R., Wang, P., Boufounos, P.T., Takahashi, R., "Radar-Conditioned 3D Bounding Box Diffusion for Indoor Human Perception", IEEE International Conference on Computer Vision (ICCV) Workshop, October 2025.
      BibTeX TR2025-154 PDF
      • @inproceedings{Yataka2025oct,
      • author = {Yataka, Ryoma and Wang, Pu and Boufounos, Petros T. and Takahashi, Ryuhei},
      • title = {{Radar-Conditioned 3D Bounding Box Diffusion for Indoor Human Perception}},
      • booktitle = {IEEE International Conference on Computer Vision (ICCV) Workshop},
      • year = 2025,
      • month = oct,
      • url = {https://www.merl.com/publications/TR2025-154}
      • }
  • MERL Contacts:
  • Research Areas:

    Computational Sensing, Computer Vision, Machine Learning, Signal Processing

Abstract:

Privacy-preserving and cost-effective indoor sensing is vital for embodied agents to collaborate safely with people in dynamic scenes. Multi-view millimeter-wave radar shows great potential for this purpose. However, prevailing methods rely on implicit cross-view association, which this reliance often results in ambiguous feature matches and de- graded performance in cluttered environments. To address these limitations, we propose REXO (multi-view Radar object dEtection with 3D bounding boX diffusiOn), which lifts DiffusionDet’s 2D box denoising to the full 3D radar space. Noisy 3D boxes are projected onto all radar views to enable explicit association and radar-conditioned denoising. Evaluated on two open indoor radar datasets, our approach out- performs state-of-the-art methods by +11.02 AP on MMVR and +4.22 AP on HIBER.

 

  • Related News & Events

    •  NEWS    MERL Papers, Workshops, and Talks at ICCV 2025
      Date: October 19, 2025 - October 23, 2025
      Where: Honolulu, HI, USA
      MERL Contacts: Petros T. Boufounos; Anoop Cherian; Toshiaki Koike-Akino; Hassan Mansour; Tim K. Marks; Pedro Miraldo; Kuan-Chuan Peng; Pu (Perry) Wang
      Research Areas: Artificial Intelligence, Computer Vision, Machine Learning, Signal Processing
      Brief
      • MERL researchers presented 3 conference papers and 3 workshop papers, co-organized 2 workshops, and delivered 2 invited talks at the IEEE International Conference on Computer Vision (ICCV) 2025, which was held in Honolulu, HI, USA from October 19-23, 2025. ICCV is one of the most prestigious and competitive international conferences in the area of computer vision. Details of MERL contributions are provided below:


        Main Conference Papers:

        1. "SAC-GNC: SAmple Consensus for adaptive Graduated Non-Convexity" by V. Piedade, C. Sidhartha, J. Gaspar, V. M. Govindu, and P. Miraldo. (Highlight Paper)
        Paper: https://www.merl.com/publications/TR2025-146

        2. "Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts" by C.-A. Yang, K.-C. Peng, and R. A. Yeh.
        Paper: https://www.merl.com/publications/TR2025-124

        3. "Manual-PA: Learning 3D Part Assembly from Instruction Diagrams" by J. Zhang, A. Cherian, C. Rodriguez-Opazo, W. Deng, and S. Gould.
        Paper: https://www.merl.com/publications/TR2025-139


        MERL Co-Organized Workshops:

        1. "The Workshop on Anomaly Detection with Foundation Models (ADFM)" by K.-C. Peng, Y. Zhao, and A. Aich.
        Workshop link: https://adfmw.github.io/iccv25/

        2. "The 8th International Workshop on Computer Vision for Physiological Measurement (CVPM)" by D. McDuff, W. Wang, S. Stuijk, T. Marks, H. Mansour, V. R. Shenoy.
        Workshop link: https://sstuijk.estue.nl/cvpm/cvpm25/


        MERL Keynote Talks at Workshops:

        1. Tim K. Marks, Keynote Speaker at the Workshop on Computer Vision for Physiological Measurement (CVPM).
        Workshop website: https://vineetrshenoy.github.io/cvpmSeptember2025/

        2. Tim K. Marks, Keynote Speaker at the Workshop on Analysis and Modeling of Faces and Gestures (AMFG).
        Workshop website: https://fulab.sites.northeastern.edu/amfg2025/


        Workshop Papers:

        1. "Joint Training of Image Generator and Detector for Road Defect Detection" by K.-C. Peng.
        paper: https://www.merl.com/publications/TR2025-149

        2. "Radar-Conditioned 3D Bounding Box Diffusion for Indoor Human Perception" by R. Yataka, P. Wang, P.T. Boufounos, and R. Takahashi.
        paper: https://www.merl.com/publications/TR2025-154

        3. "L-GGSC: Learnable Graph-based Gaussian Splatting Compression" by S. Kato, T. Koike-Akino, and T. Fujihashi.
        paper: https://www.merl.com/publications/TR2025-148
    •