Shuhong Liu

PhD Candidate of The University of Tokyo, Tokyo, Japan.

prof_pic.jpg

Department of Mechano-Informatics

Graduate School of Information Science and Technology

The University of Tokyo

Greatings! I am currently pursuing my PhD degree at the Machine Intelligence Laboratory (MIL) under the supervision of Prof. Tatsuya Harada. Before that, I obtained my Master’s degree from the Intelligent Systems and Informatics (ISI) Laboratory at the Graduate School of Information Science and Technology, University of Tokyo, where I was supervised by Prof. Kohei Nakajima and Prof. Yasuo Kuniyoshi. I received my Bachelor degree of Engineering in University of Waterloo, ON, Canada.

My research interests are centered around 3D Computer Vision, Robotics, and Computational Photography. Currently, my work focuses on integrating physical priors into 3D world modeling to bridge the gap between data-driven and physics-based learning methodologies.

News

Feb 19, 2026 Co-organizing 1st 3D Restoration and Reconstruction (3DRR) Challenge on NTIRE & CVPR 2026 ! Two Tracks Online ! :sparkles:
Feb 07, 2026 Co-organizing Efficient Super-Resolution Challenge on NTIRE & CVPR 2026 ! :sparkles:
Jan 10, 2026 Serving as Program Committee at 3rd AI for Content Generation, Quality Enhancement and Streaming (AI4Streaming) Workshop at CVPR 2026 ! :sparkles:

Selected Publications

(* indicates equal contribution)

  1. Preprint
    xlens_cover.gif
    X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras
    Heng Zhou*, Shuhong Liu*, Yonghao He, Bohao Zhang, Fa Fu, Chenhui Hou, Xianbao Hou, Lijun Han, and Wei Sui
    In Technical Report, 2026
    arXiv Code Website
  2. Preprint
    rawild_teaser.jpg
    RAWild: Sensor-Agnostic RAW Object Detection via Physics-Guided Curve and Grid Modeling
    Shuhong Liu, Gengjia Chang, Jun Liu, Xuangeng Chu, Yinqiang Zheng, Tatsuya Harada, and Ziteng Cui
    In preprint, 2026
    arXiv Code
  3. Preprint
    fluxflow_teaser.jpg
    FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution
    Shuhong Liu, Xining Ge, Ziteng Cui, Liuzhuozheng Li, Gengjia Chang, Jun Liu, Ziying Gu, Dong Li, Xuangeng Chu, Lin Gu, and others
    In preprint, 2026
    arXiv
  4. CVPRW
    ntire_logo.png
    NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results
    Shuhong Liu, Chenyu Bao, Ziteng Cui, Xuangeng Chu, Bin Ren, Lin Gu, Xiang Chen, Mingrui Li, Long Ma, Marcos V. Conde, Radu Timofte, and et al.
    In Proceedings of the Computer Vision and Pattern Recognition Conference Workshops, 2026
    arXiv Code
  5. ECCV
    denoise_sky_teaser.jpg
    Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging
    Shuhong Liu, Xining Ge, Ziying Gu, Lin Gu, Ziteng Cui, Xuangeng Chu, and et al.
    In European Conference on Computer Vision (ECCV), 2026
    arXiv Code
  6. IJCV
    realx3d_cover.gif
    RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstruction
    Shuhong Liu, Chenyu Bao, Ziteng Cui, Yun Liu, Xuangeng Chu, Lin Gu, and et al.
    In International Journal of Computer Vision (IJCV), 2026
    arXiv Code Website
  7. NeurIPS
    I2_NeRF_cover.gif
    I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions
    Shuhong Liu, Lin Gu, Ziteng Cui, Xuangeng Chu, and Tatsuya Harada
    In The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
    DOI arXiv Code Website
  8. TVCG
    dense_cover.gif
    DenseSplat: Densifying Gaussian Splatting SLAM with Neural Radiance Prior
    Mingrui Li*, Shuhong Liu*, Tianchen Deng, and Hongyu Wang
    IEEE Transactions on Visualization and Computer Graphics (TVCG), 2025
    DOI arXiv Video
  9. TASE
    mg_cover.png
    MG-SLAM: Structure Gaussian Splatting SLAM With Manhattan World Hypothesis
    Shuhong Liu, Tianchen Deng, Heng Zhou, Liuzhuozheng Li, Hongyu Wang, Danwei Wang, and Mingrui Li
    IEEE Transactions on Automation Science and Engineering (TASE), 2025
    DOI arXiv
  10. PRR
    prr_cover.png
    Exploiting chaotic dynamics as deep neural networks
    Shuhong Liu, Nozomi Akashi, Qingyao Huang, Yasuo Kuniyoshi, and Kohei Nakajima
    Physical Review Research, 2025
    DOI arXiv Code
  11. AAAI
    DeRainGS_cover.gif
    DeRainGS: Gaussian Splatting for Enhanced Scene Reconstruction in Rainy Environments
    Shuhong Liu, Xiang Chen, Hongming Chen, Quanfeng Xu, and Mingrui Li
    In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2025
    DOI arXiv Website
  12. ECCV
    sgs_cover.gif
    SGS-SLAM: Semantic Gaussian Splatting for Neural Dense SLAM
    Mingrui Li*, Shuhong Liu*, Heng Zhou, Guohao Zhu, Na Cheng, Tianchen Deng, and Hongyu Wang
    In European Conference on Computer Vision (ECCV), 2024
    DOI arXiv Video Code

Honors and Awards

Jul 18, 2026 The Chinese Government Award for Outstanding Self-financed Students Abroad (30 fellows in Japan) :sparkles:
Sep 15, 2024 BOOST NAIS Next-Generation AI for Intelligent Society, Japan Science and Technology Agency (JST), 2024.10 - 2027.09, (4–6 fellows per cohort) :sparkles:
May 27, 2024 Winner of CVPR 2024 UG2+ UAV Tracking and Pose Estimation (Track-3) :sparkles:

Services

Reviewer NeurIPS, ICLR, ICML, CVPR, ICCV, AAAI, TRO, TMLR, PR