Dr Fan (Aaron) Zhang

Senior Lecturer
in Visual Communications

School of Computer Science
University of Bristol
fan.zhang@bristol.ac.uk



About

I am a Senior Lecturer in Visual Communications within the School of Computer Science, University of Bristol. I am also a member of the Visual Information Laboratory and the Bristol Vision Institute, which are led by Prof. David Bull. I have been involved in many research projects on video compression, quality assessment, image processing and creative technology. I have published over 80 academic papers, and have contributed to two books on video compression. My work on super-resolusion-based video compression, and deep video coding training database has contributed to international standardization processes. I was a co-winner of the 2017 IEEE ICIP Grand Challenge on Video Compression and the 2023 IEEE/CVF WACV Grand Challenge on HDR Video Quality Measurement. I am currently an associate editor of IEEE TCSVT (2021-present), and has been serving as a reviewer for a number of top tier conferences and journals including CVPR, WACV, TIP, TMM, SPL and TCSVT. I am also a member of the Visual Signal Processing and Communications Technical Committee associated with the IEEE Circuits and Systems Society.

Important Download Links


Teaching

  • EENGM4021 Image and Video Coding (Unit Director: Prof David Bull)
  • EENGM0004 Engineering Research Skills (Unit Director)
  • COMSM0129 Augmenting the Real World (Unit Director)

News & Activities

[Older news and activities]


Primary Research Areas


Signature Research Projects


arXiv 2024

MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution
Yuxuan Jiang, Chen Feng, Fan Zhang, David Bull
arXiv, 2024
[arXiv]


AAAI 2024

LDMVFI: Video Frame Interpolation with Latent Diffusion Models
Duolikun Danier, Fan Zhang, David Bull
AAAI Conference on Artificial Intelligence (AAAI), 2024
[arXiv] [code]

WACV 2024

RankDVQA: Deep VQA based on Ranking-inspired Hybrid Training
Chen Feng, Duolikun Danier, Fan Zhang, David Bull
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024
[arXiv] [project] [code]

NeurIPS 2023

HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation
Ho Man Kwan, Ge Gao, Fan Zhang, Andrew Gower, David Bull
Conference on Neural Information Processing Systems (NeurIPS), 2023
[arXiv] [project] [code]

TIP 2023

BVI-VFI: A Video Quality Database for Video Frame Interpolation
Duolikun Danier, Fan Zhang, David Bull
IEEE Transactions on Image Processing (TIP), 2023
[paper] [arXiv] [project] [database] [github]

CVPR 2022

ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation
Duolikun Danier, Fan Zhang, David Bull
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
[arXiv] [project] [code]

TMM 2021

BVI-DVC: A Training Database for Deep Video Compression
Di Ma, Fan Zhang, David Bull
IEEE Transactions on Multimedia (TMM), 2021
[paper] [arXiv] [project] [database]


Full Publication List


Book and Book Chapters
  1. Intelligent Image and Video Compression: Communicating Pictures. [book][resource]
    D. Bull and F. Zhang, 2nd Edition, Oxford: Academic Press, 2021.

  2. Measuring video quality. [book]
    F. Zhang and D. Bull, In: Sergios Theodoridis and Rama Chellappa, editors, Academic Press Library in Signal Processing. Vol 5. , Oxford: Academic Press, 2014, pp 227-249. ISBN: 978-0-12-420149-1.
MPEG Standard Contributions
  1. Description of SDR video coding technology proposal by University of Bristol (JVET-J0031) [document]
    D. Bull, F. Zhang and M. Afonso, A submission to the Joint Call for Proposals on Video Compression with Capability beyond HEVC, April 2018 in San Diego.

  2. BVI_Texture UHD 120fps test sequences for HEVC and beyond (JCTVC-V0099) [document]
    M. Papadopoulos, F. Zhang, D. Agrafiotis, D. Bull and J.-R. Ohm, October 2015 in Geneva.

arXiv Papers
  1. MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution. [paper]
    Y. Jiang, C. Feng, F. Zhang, D. Bull, arXiv:2404.09571, 2024.

  2. Enhancing HDR Video Compression through CNN-based Effective Bit Depth Adaptation. [paper]
    C. Feng, Z. Qi, D. Danier, F. Zhang, X. Xu, S. Liu, D. Bull, arXiv:2207.08634, 2022.

Journal Papers
  1. CVEGAN: a perceptually-inspired GAN for compressed video enhancement. [paper][project & code]
    D. Ma, F. Zhang, and D. R. Bull, accepted by Signal Processing: Image Communication, 2024.

  2. BVI-VFI: A Video Quality Database for Video Frame Interpolation. [paper][project & database]
    D. Danier, F. Zhang and D. Bull, IEEE Trans. on Image Processing, 2024.

  3. A multiple-UAV architecture for autonomous media production. [paper]
    I. Mademlis, A. Torres-Gonzalez, J. Capitan, M. Montagnuolo, A. Messina, F. Negro, C. Le Barz, T. Goncalves, R. Cunha, B. Guerreiro, F. Zhang, S. Boyle, G. Guerout, A. Tefas, N. Nikolaidis, D. Bull and I. Pitas, Multimedia Tools and Applications, 2023.

  4. BVI-CC: A Dataset for Research on Video Compression and Quality Assessment. [paper][dataset]
    A. V. Katsenou, F. Zhang, M. Afonso, G. Dimitrov and D. R. Bull, Frontiers in Signal Processing, 2022.

  5. Optimising VVC Encoding Using Key Frame Selection. [paper]
    S. Nagaraju, F. Zhang, S. Takamura, D. R. Bull, IIEEJ Transactions On Image Electronics, 2021.

  6. BVI-DVC: A Training Database for Deep Video Compression. [paper][dataset]
    D. Ma, F. Zhang, and D. R. Bull, IEEE Trans. on Multimedia, 2021.

  7. ViSTRA2: Video Coding using Spatial Resolution and Effective Bit Depth Adaptation. [paper][project]
    F. Zhang, M. Afonso and D. R. Bull, Elsevier Signal Processing Image Communication, 2021.

  8. Video Compression with CNN-based Post Processing. [paper][project]
    F. Zhang, D. Ma, C. Feng and D. R. Bull, IEEE MultiMedia Magazine, 2020.

  9. MFRNet: A New CNN Architecture for Post-Processing and In-loop Filtering. [paper]
    D. Ma, F. Zhang, and D. R. Bull, IEEE Journal of Selected Topics in Singal Processing, 2020.

  10. A Study of High Frame Rate Video Formats. [paper][project][dataset]
    A. Mackin, F. Zhang, and D. R. Bull, IEEE T-MM, 2019.

  11. Video Compression based on Spatio-Temporal Resolution Adaptation. [paper][project]
    M. Afonso, F. Zhang and D. R. Bull, IEEE T-CSVT (Letter), 2019.

  12. Rate-distortion Optimization Using Adaptive Lagrange Multipliers. [paper][project]
    F. Zhang and D. R. Bull, IEEE T-CSVT, 2019.

  13. BVI-HD: A Video Quality Database for HEVC Compressed and Texture Synthesised Content. [paper][dataset]
    F. Zhang, F. Mercer Moss, R. Baddeley and D. R. Bull, IEEE T-MM, 2018.

  14. Reduced-Reference Video Quality Metric Using Spatial Information in Salient Regions. [paper]
    F. D. A. Rahman, D. Agrafiotis, O. O. Khalifa and F. Zhang, TELKOMNIKA (Telecommunication Computing Electronics and Control), 2018.

  15. On the Optimal Presentation Duration for Subjective Video Quality Assessment. [dataset][project]
    F. Mercer Moss, K. Wang, F. Zhang, R. Baddeley and D. Bull, IEEE T-CSVT, November 2016.

  16. Support for Reduced Presentation Durations in Subjective Video Quality Assessment. [paper][project]
    F. Mercer Moss, C.-T. Yeh, F. Zhang, R. Baddeley, D. R. Bull, Elsevier Signal Processing: Image Communication, October 2016.

  17. A Perception-based Hybrid Model for Video Quality Assessment [paper][code][project]
    F. Zhang and D. Bull, IEEE T-CSVT, June 2016.

  18. Perception-oriented Video Coding based on Image Analysis and Completion: a Review. [paper]
    P. Ndjiki-Nya, D. Doshkov, H. Kaprykowsky, F. Zhang, D. Bull, T. Wiegand, Signal Processing: Image Communication, July 2012.

  19. A Parametric Framework For Video Compression Using Region-based Texture Models. [paper][project]
    F. Zhang and D. Bull, IEEE J-STSP, November 2011.
Conference Contributions
  1. LDMVFI: Video Frame Interpolation with Latent Diffusion Models. [paper][source code]
    D. Danier, F. Zhang, D. Bull, accepted by AAAI, 2024.

  2. RankDVQA: Deep VQA based on Ranking-inspired Hybrid Training. [paper][source code]
    C. Feng, D. Danier, F. Zhang, and D. R. Bull, IEEE/CVF WACV 2024.

  3. Immersive Video Compression using Implicit Neural Representations. [paper]
    H M Kwan, F Zhang, A Gower, D Bull, accepted by PCS, 2024.

  4. Compressing Deep Image Super-resolution Models. [paper][source code]
    Y Jiang, J Nawala, F Zhang, D Bull, accepted by PCS, 2024.

  5. Full-reference Video Quality Assessment for User Generated Content Transcoding. [paper]
    Z Qi, C Feng, D Danier, F Zhang, X Xu, S Liu, D Bull, accepted by PCS, 2024.

  6. RankDVQA-mini: Knowledge Distillation-Driven Deep Video Quality Assessment. [paper]
    C Feng, D Danier, H Wang, F Zhang, D Bull, accepted by PCS, 2024.

  7. BVI-Artefact: An Artefact Detection Benchmark Dataset for Streamed Videos. [paper]
    C Feng, D Danier, F Zhang, D Bull, accepted by PCS, 2024.

  8. Accelerating Learnt Video Codecs with Gradient Decay and Layer-wise Distillation. [paper]
    T Peng, G Gao, H Sun, F Zhang, D Bull, accepted by PCS, 2024.

  9. HiNeRV: Video Compression with Hierarchical Encoding based Neural Representation. [paper][source code]
    Ho Man Kwan, Ge Gao, Fan Zhang, Andrew Gower, David Bull, NeurIPS 2023.

  10. ST-MFNet Mini: Knowledge Distillation-Driven Frame Interpolation. [paper][source code]
    C. Morris, D. Danier, F. Zhang, N. Anantrasirichai and D. Bull, ICIP, 2023.

  11. ST-MFNet: Spatio-Temporal Multi-Flow Network for Video Frame Interpolation. [paper][project & Code]
    D. Danier, F. Zhang, and D. R. Bull, IEEE/CVF CVPR, 2022

  12. Analysis of video quality induced spatio-temporal saliency shifts. [paper]
    X. Wu, Z. Dong, F. Zhang, P. L. Rosin and H. Liu, IEEE ICIP, 2022

  13. Identifying pitfalls in the evaluation of saliency models for videos. [paper]
    Z. Dong, X. Wu, X. Zhao, F. Zhang, and H. Liu, IEEE IVMSP Workshops, 2022

  14. FloLPIPS: A Bespoke Video Quality Metric for Frame Interpoation. [paper][project & Code]
    D. Danier, F. Zhang, and D. Bull, PCS, 2022.

  15. Enhancing VVC with Deep Learning based Multi-Frame Post-Processing. [paper]
    D. Danier, C. Feng, F. Zhang, and D. R. Bull, 5th Challenge on Learned Image Compression (in IEEE/CVF CVPR), 2022

  16. Enhancing Deformable Convolution based Video Frame Interpolation with Coarse-to-fine 3D CNN. [paper][project & code]
    D. Danier, F. Zhang, and D. R. Bull, accepted by ICIP 2022.

  17. A CNN-based Post-Processor for Perceptually-Optimized Immersive Media Compression. [paper]
    A. Katsenou, F. Zhang, and D. R. Bull, accetpted by ICIP 2022.

  18. A Subjective Quality Study for Video Frame Interpolation. [paper][project]
    D. Danier, F. Zhang, and D. R. Bull, accetpted by ICIP 2022.

  19. ViSTRA3: Video Coding with Deep Parameter Adaptation and Post Processing. [paper]
    C. Feng, D. Danier, C. Tan, F. Zhang, D. Bull, Grand Challenge on Neural Network-based Video Coding in IEEE ISCAS, 2022

  20. Enhancing VMAF through New Feature Integration and Model Combination. [paper]
    Fan Zhang, Angeliki Katsenou, Christos Bampis, Lukas Krasula, Zhi Li and David Bull, PCS, 2021.

  21. A Subjective Study on Videos at Various Bit Depths. [paper]
    Alex Mackin, Di Ma, Fan Zhang and David Bull, PCS, 2021.

  22. VMAF-based Bitrate Ladder Estimation for Adaptive Streaming. [paper]
    Angeliki V. Katsenou, Fan Zhang, Kyle Swanson, Mariana Afonso, Joel Sole and David R. Bull, PCS, 2021.

  23. Key Reference Frame Selection for VVC Encoding. [paper]
    S. Nagaraju, F. Zhang, S. Takamura, D. R. Bull, Proceedings of the 49th Annual Conference of the Institute of Image Electronics Engineers of Japan, 2021.

  24. Enhancing VVC through CNN-based Post-Processing. [paper][project]
    F. Zhang, C. Feng and D. Bull, ICME, 2020.

  25. A Simulation Environment for Drone Cinematography. [paper]
    F. Zhang, D. Hall, T. Xu, S. Boyle and D. Bull, IBC, 2020.

  26. Video compression with low complexity CNN-based spatial resolution adaptation. [paper]
    D. Ma, F. Zhang, and D. Bull, SPIE, 2020.

  27. GAN-based Effective Bit Depth Adaptation for Perceptual Video Compression. [paper]
    D. Ma, F. Zhang and D. Bull, ICME, 2020.

  28. Encoding in the Dark Grand Challenge: An Overview. [paper]
    N. Anantrasirichai, F. Zhang, A. Malyugina, P. Hill, A. Katsenou, ICME Workshops, 2020.

  29. Enhanced Video Compression based on Effective Bit Depth Adaptation. [paper]
    F. Zhang, M. Afonso and D. Bull, ICIP, 2019.

  30. A Subjective Study of Viewing Experience for Drone VIdeos Using Simulated Content. [paper]
    S. Boyle, F. Zhang and D. Bull, ICIP, 2019.

  31. A Subjective Comparison of AV1 and HEVC for Adaptive Video Streaming. [paper][dataset]
    A. Katsenou, F. Zhang, M. Afonso and D. Bull, ICIP, 2019.

  32. Frame Rate Conversion Method based on a Virtual Shutter Angle. [paper]
    A. Mackin, F. Zhang and D. Bull, ICIP, 2019.

  33. Environment Capture and Simulation for UAV Cinematography Planning and Training. [paper]
    S. Boyle, M. Newton, F. Zhang and D. Bull, EUSIPCO, 2019.

  34. Perceptually-inspired Super-resolution of Compressed Videos. [paper]
    D. Ma, M. Afonso, F. Zhang and D. Bull, SPIE, 2019.

  35. The Future of Media Production Through Multi-drones' Eyes. [paper]
    A. Messina, S. Metta, M. Montagnuolo, F. Negro, V. Mygdalis, I. Pitas, J. Capitan, A. Torres, S. Boyle, D. Bull and F. Zhang, IBC, 2018.

  36. A study of subjective video quality at various spatial resolutions. [paper][dataset]
    A. Mackin, M. Afonso, F. Zhang and D. Bull, ICIP, 2018.

  37. Spatial resolution adaptation framework for video compression. [paper]
    M. Afonso, F. Zhang and D. Bull, SPIE, 2018.

  38. SRQM: A Video Quality Metric for Spatial Resolution Adaptation. [paper][code]
    A. Mackin, M. Afonso, F. Zhang and D. Bull, PCS, 2018.

  39. A Frame Rate Dependent Video Quality Metric based on Temporal Wavelet Decomposition and Spatiotemporal Pooling. [paper][code]
    F Zhang, A Mackin and D. R. Bull, ICIP, 2017.

  40. Low Complexity Video Coding Based on Spatial Resolution Adaptation. [paper]
    M. Afonso, F. Zhang, A. Katsenou, D. Agrafiotis, D. Bull, ICIP, 2017.

  41. Investigating the Impact of High Frame Rates on Video Compression. [paper][dataset]
    A. Mackin, F. Zhang, M. A. Papadopoulos, D. Bull, ICIP, 2017.

  42. Video Texture Analysis based on HEVC Encoding Statistics. [paper][dataset]
    M. Afonso, A. Katsenou, F. Zhang, D. Agrafiotis, D. Bull, PCS, 2016.

  43. HEVC Enhancement using Content-based Local QP Selection. [paper]
    F. Zhang and D. Bull, ICIP, 2016.

  44. An Adaptive QP Offset Determination Method for HEVC. [paper]
    M. A. Papadopoulos, F. Zhang, D. Agrafiotis, D. R. Bull, ICIP, 2016.

  45. What's on TV: A Large Scale Quantitative Characterisation of Modern Broadcast Video Content. [paper][project]
    F. Mercer Moss, F. Zhang, R. Baddeley, D. R. Bull, ICIP, 2016.

  46. An Adaptive Lagrange Multiplier Determination Method for Rate-distortion Optimisation in Hybrid Video Codecs. [paper][project]
    F. Zhang and D. Bull, ICIP, 2015.

  47. A Study of Subjective Video Quality at Various Frame Rates. [paper][dataset]
    A. Mackin, F. Zhang and D. Bull, ICIP, 2015.

  48. A Very Low Complextiy Reduced Reference Video Quality Metric based on Spatio-temporal Information Selection. [paper]
    M. Wang, F. Zhang and D. Agrafiotis, ICIP, 2015.

  49. A Video Texture Database for Perceptual Compression and Quality Assessment. [paper][dataset]
    M. A. Papadopoulos, F. Zhang, D.Agrafiotis and D. Bull, ICIP, 2015.

  50. Optimal sequence duration for subjective video quality assessment. [paper][project]
    F. J. Mercer Moss, K. Wang, F. Zhang, R. Baddeley and D. Bull, SPIE Optical Engineering+ Applications, 2015.

  51. Quality Assessment Methods for Perceptual Video Compression. [paper][code][project]
    F. Zhang and D. Bull, ICIP, Melbourne, Australia, September 2013.

  52. Production of high dynamic range video. [paper]
    M. Price, D. Bull, T. Flaxton, S. Hinde, R. Salmon, A. Sheikh, G. Thomas, and F. Zhang, IBC, Amsterdam, September, 2013.

  53. Advances in Region-based Texture Modeling for Video Compression. [paper][project]
    F. Zhang and D. Bull, Proc. SPIE 8135, San Diego, USA, August, 2011.

  54. Enhanced Video Compression With Region-Based Texture Models. [paper][project]
    F. Zhang and D. Bull, PCS, Nagoya, Japan, December, 2010.

  55. Region-Based Texture Modelling For Next Generation Video Codecs [paper][project]
    F. Zhang, D. Bull, and N. Canagarajah, ICIP, Hong Kong, China, September, 2010.
Other Publications
  1. Exploring the Challenges of Higher Frame Rates: from Quality Assessment to Frame Rate Selection. [paper][project]
    A. V. Katsenou, A. Mackin, D. Ma, F. Zhang and D. R. Bull, IEEE COMSOC MMTC Communications - Frontiers (E-Letter), May 2018 (invited).