Ho Man Kwan

PhD Student

University of Bristol

hm.kwan@bristol.ac.uk



About

I am currently a PhD student (Oct 2022 - Present) at the Visual Information Laboratory, University of Bristol. My research is supervised by Prof. David Bull and Dr. Aaron Zhang. My research is funded by EPSRC (iCASE), BT, and the UKRI MyWorld Strength in Places Programme. My research interests include deep video compression and volumetric video compression, particularly based on neural representations.


Activities

  • Dec 2024: Our paper on "PNVC: Towards Practical INR-based Video Compression" has been accepted by AAAI 2025.
  • Sep 2024: Our paper on "NVRC: Neural Video Representation Compression" has been accepted by NeurIPS 2024.
  • Sep 2024: Our team won first place in the End-to-End Video Compression Track (Track 2) at the 3rd Practical End-to-End Image/Video Compression Challenge in IEEE MMSP 2024.
  • Feb 2023: Our paper on "Immersive Video Compression using Implicit Neural Representations" has been accepted by PCS 2024.
  • Sep 2023: Our paper on "HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation" has been accepted by NeurIPS 2023.

  • Publications

    • PNVC: Towards Practical INR-based Video Compression. [arXiv]
      G. Gao, H. M. Kwan, F. Zhang and D. Bull, AAAI 2025 (Accepted)

    • NVRC: Neural Video Representation Compression. [arXiv]
      H. M. Kwan, G. Gao, F. Zhang, A. Gower and D. Bull, NeurIPS 2024

    • Immersive Video Compression using Implicit Neural Representations. [arXiv]
      H. M. Kwan, F. Zhang, A. Gower and D. Bull, PCS 2024

    • HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation. [project][arXiv][Code]
      H. M. Kwan, G. Gao, F. Zhang, A. Gower and D. Bull, NeurIPS 2023

    • SSBNet: Improving Visual Recognition Efficiency by Adaptive Sampling. [arXiv]
      H. M. Kwan and S. Song, ECCV 2022

    Preprints

    • HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution. [arXiv]
      Y. Jiang, H. M. Kwan, T. Peng, G. Gao, F. Zhang, X. Zhu, J. Sole and D. Bull, arXiv 2024

    • BVI-CR: A Multi-View Human Dataset for Volumetric Video Compression. [arXiv]
      G. Gao, A. Azzarelli, H. M. Kwan, N. Anantrasirichai, F. Zhang, O. Moolan-Feroze and D.Bull, arXiv 2024

    • FedSDD: Scalable and Diversity-enhanced Distillation for Model Aggregation in Federated Learning. [arXiv]
      H. M. Kwan and S. Song, arXiv 2023