Dongting Hu Ph.D. Student Melbourne Deep Learning Group School of Mathematics and Statistics The University of Melbourne Address: 206 Old Geology Building South, Parkville, VIC, Australia Email: dongting AT student.unimelb.edu.au

Biography

I am a Ph.D. student at the School of Mathematics and Statistics, the University of Melbourne (UoM). I am interested in advanced topics within computer vision and generative models, with a focus on refining image manipulation and generation techniques. My work involves exploring methodologies for Neural Radiance Fields, aimed at constructing efficient, high-fidelity volumetric scenes, and developing effective neural scene editing techniques. Currently, my interests lie in generative AI, including 2D text-to-image generation and 3D assets generation for novel view synthesis.

Education Background

• Ph.D. student, 2021.09 - 2025.03 (expected)
  The University of Melbourne, Victoria, Australia.
  Principle supervisor: Dr. Mingming Gong.
  Co-supervisor: Dr. Liuhua Peng and Dr. Tingjin Chu.

• M.S. Data science, 2020.03 - 2021.07
  The University of Melbourne, Victoria, Australia.

• G.D. Data science, 2019.02 - 2020.01
  The University of Melbourne, Victoria, Australia.

• B.E. Mechanical Engineering, 2014.09 - 2018.07
  Donghua University, Shanghai, China.

Publications

• In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment
  D. Hu, H. Fu, J. Guo, L. Peng, T. Chu, F. Liu, T. Liu, M. Gong
  Advances in Neural Information Processing Systems (NeurIPS 2024).
  

• Multiscale Representation for Real-Time Anti-Aliasing Neural Rendering
  D. Hu, Z. Zhang, T. Hou, T. Liu, H. Fu^*, M. Gong^*
  International Conference on Computer Vision (ICCV 2023).
  

• Uncertainty Quantification in Depth Estimation via Constrained Ordinal Regression
  D. Hu, L. Peng, T. Chu, X. Zhang, Y. Mao, H. Bondell, M. Gong
  European Conference on Computer Vision (ECCV 2022).
  

• STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario
  R. Liu, K. Lam, W. Zhou, S. Wu, J. Zhao, D. Hu, M. Gong
  IEEE Transactions on Multimedia.
  

• Generating imperceptible adversarial examples by flow field and normalize flow-based model
  R. Liu, X. Jin, D. Hu, J. Zhang, Y. Wang, J. Zhang, W. Zhou
  Frontiers in Neurorobotics.
  

Honors and Awards

• Melbourne Research Scholarship, 2021-2025.

• Science Abroad Travelling Scholarship (SATS), 2023

Invited Talks

• “Uncertainty Quantification in Depth Estimation via Constrained Ordinal Regression”, AI TIME, Dec 7, 2022 (online)

Academic Service

• Conference Reviewer/Program Committee: ICLR, ECCV, BMVC, ECAI, AJCAI, etc.

• Journal Reviewer: Neural Networks, Frontiers in Computer Science, etc.

Tutoring Roles

• MAST90138 - Multivariate Statistics for Data Science.

• MAST90104 - A First Course in Statistical Learning.

• MAST90082 - Mathematical Statistics.

• MAST30025 - Linear Statistical Models.

• MAST20005 - Statistics.

© Dongting Hu | Last update: Sep. 2024