I am a Research Fellow in the Faculty of Information Technology at Monash University, working with Prof. Zongyuan Ge. I recently completed my PhD at the Australian National University in mid-2026 under the supervision of Prof. Hongdong Li. My research spans a broad range of topics in artificial intelligence and computer vision, including 3D vision, medical imaging, AI for Science, and robotics.

Beyond research, I am an enthusiastic photographer, especially of wildlife and landscapes. I also enjoy sports such as hiking, bouldering, fishing, and kayaking. Follow my RedNote and Instagram for beautiful photos.

🔥 News

  • 2026.07: Moved to Melbourne to start my Research Fellowship at Monash University.
  • 2026.06: One paper accepted to ECCV 2026.
  • 2026.04: Passed my PhD oral examination and submitted my thesis.

📖 Education

  • 2021.04 - Present, Doctor of Philosophy in Engineering and Computer Science, Australian National University, Australia.
  • 2018.07 - 2020.07, Bachelor of Engineering (First Class Honours), ANU-NPU joint 2+2 program, Australian National University, Australia.
  • 2016.09 - 2018.07, Bachelor of Engineering, Northwestern Polytechnical University, China.

💻 Work Experience

  • 2026.07 - Present, Faculty of Information Technology, Monash University, Research Fellow.
  • 2025.01 - 2025.07, International Machine Learning, Amazon, Research Intern.
  • 2022.07 - 2023.04, XR Vision Labs, Tencent, Research Intern.

📝 Publications

ECCV 2026
sym

XPos3R: Cross-Modal Transformer for Intraoperative 2D/3D Registration

Shiyan Su*, Ruyi Zha*, Hongdong Li, Xuelian Cheng, Zongyuan Ge

The 19th European Conference on Computer Vision (ECCV) 2026

arXiv TBD

  • We propose a DUSt3R-like framework for intraoperative 2D/3D registration.
CVPR 2026
sym

Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors

Rong Wang, Ruyi Zha, Ziang Cheng, Jiayu Yang, Pulak Purkait, Hongdong Li

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026

arXiv

  • We leverage shape priors from 3D foundation model to improve video generation.
AAAI 2026
sym

DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction

Shiyan Su*, Ruyi Zha*, Danli Shi, Hongdong Li, Xuelian Cheng

The 40th Annual AAAI Conference on Artificial Intelligence (AAAI) 2026

arXiv, Code

  • We use diffusion models to improve neural representation learning for CT reconstruction.
TMI 2026
sym

Three-Dimensional MRI Reconstruction with Gaussian Representations: Tackling the Undersampling Problem

Tengya Peng, Ruyi Zha, Zhen Li, Xiaofeng Liu, Qing Zou

Transactions on Medical Imaging (TMI) 2026

arXiv

  • We extend the idea of 3DGS to MRI reconstruction.
3DV 2026
sym

X-LRM: X-ray Large Reconstruction Model for Extremely Sparse-View Computed Tomography Recovery in One Second

Guofeng Zhang*, Ruyi Zha*, Hao He, Yixun Liang, Alan Yuille, Hongdong Li, Yuanhao Cai

International Conference on 3D Vision (3DV) 2026

arXiv

  • We propose a feedforward NeRF-like method for sparse-view CT reconstruction.
IPMI 2025 (Oral)
sym

4DRGS: 4D Radiative Gaussian Splatting for Efficient 3D Vessel Reconstruction from Sparse-View Dynamic DSA Images

Zhentao Liu*, Ruyi Zha*, Huangxuan Zhao, Hongdong Li, Zhiming Cui

Information Processing in Medical Imaging (IPMI) 2025

arXiv, Code, Project

  • We extend R$^2$-Gaussian to digital subtraction angiography.
ICCV 2025
sym

X$^2$-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstruction

Weihao Yu, Yuanhao Cai, Ruyi Zha, Zhiwen Fan, Chenxin Li, Yixuan Yuan

International Conference on Computer Vision (ICCV) 2025

arXiv, Code, Project

  • We extend R$^2$-Gaussian to 4D CT reconstruction.
NeurIPS 2024
sym

R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction

Ruyi Zha, Tao Jun Lin, Yuanhao Cai, Jiwen Cao, Yanhao Zhang, Hongdong Li

The 38th Annual Conference on Neural Information Processing Systems (NeurIPS) 2024

arXiv, Code

  • We present the first 3DGS-like framework for CT reconstruction.
MICCAI 2023 (Oral)
sym

EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videos

Ruyi Zha*, Xuelian Cheng*, Hongdong Li, Mehrtash Harandi, Zongyuan Ge

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2023 (Oral)

arXiv, Code

  • We present a NeRF-based method for recovering deformable tissues from endoscopic videos.
MICCAI 2022 (Oral)
sym

NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction

Ruyi Zha, Yanhao Zhang, Hongdong Li

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2022 (Oral)

arXiv, Code

  • We present a NeRF-like framework for CT reconstruction.

🎖 Honors and Awards

  • 2021, Australian Government Research Training Program International Scholarship.
  • 2019, ANU Summer Research Scholarship.
  • 2016, China National Scholarship.