About Me

I am currently a Researcher and Engineer in video processing team at Zoom, based in Singapore. Before joining Zoom, I was a Postdoctoral Fellow in the Department of Electrical and Electronic Engineering at The Hong Kong Polytechnic University, supervised by Prof. Kin-Man Lam. Before PhD graduation, I was interned at Microsoft Research Asia.

Research Interests

  • AIGC (post-training): image/video generation, world model, efficient generative models, and preference optimization.
  • Low-level vision processing: image/video super-resolution, image/video denoising, and high dynamic range imaging.
  • 3D vision: generative-based 3D reconstruction

I am actively seeking opportunities for research collaboration. Please feel free to reach out via email at jun.xiao@connect.polyu.hk, WeChat, or WhatsApp.

Work Authorization

I am currently authorized to work in Mainland China, Hong Kong, the United Kingdom under the HPI visa, and Canada, pending approval of my Open Work Permit (OWP).

I am also open to opportunities in the United States, provided that O-1 visa sponsorship is available.

Download my CV .

Education

  • Ph.D., The Hong Kong Polytechnic University (PolyU), 2018.09 -- 2022.10

  • M.S.c (with distinction), The Hong Kong Polytechnic University (PolyU), 2016.09 -- 2018.03

  • BSc, Guangdong University of Technology, 2012.09 -- 2016.06

Publications

Kin-Chung Chan, Jun Xiao, Hana Lebeta Goshu, Kin-Man Lam (2024). Point Cloud Densification for 3D Gaussian Splatting from Sparse Input Views. In ACM MM.

Zhi-Song Liu, Li-Wen Wang, Jun Xiao, Vicky Kalogeiton (2024). Bridging Text and Image for Artist Style Transfer via Contrastive Learning. In ECCV-W.

Jun Xiao, Zihang Lyu, Hao Xie, Cong Zhang, Yakun Ju, Changjian Shui, Kin-Man Lam (2024). Frequency-Aware Guidance for Blind Image Restoration via Diffusion Models. In ECCV-W.

Jun Xiao, Changjian Shui, Zhi-Song Liu, Qian Ye, Kin-Man Lam (2024). Learning Equilibrium Transformation for Gamut Expansion and Color Restoration. In ECCV.

Yushen Zuo, Jun Xiao, Kin-Chung Chan, Rongkang Dong, Cuixin Yang, Zongqi He, Hao Xie, Kin-Man Lam (2024). Towards Multi-View Consistent Style Transfer with One-Step Diffusion via Vision Conditioning. In ECCV-W.

Jun Xiao, Zihang Lyu, Cong Zhang, Yakun Ju, Changjian Shui, Kin-Man Lam (2024). Towards Progressive Multi-Frequency Representation for Image Warping. In CVPR.

Jun Xiao, Qian Ye, Tianshan Liu, Cong Zhang, Kin-Man Lam (2024). Deep Progressive Feature Aggregation Network for Multi-frame High Dynamic Range Imaging. In Neurocomputing.

Jun Xiao, Qian Ye, Rui Zhao, Kin-Man Lam, Kao Wan (2024). Deep Multi-scale Feature Mixture Model for Image Super-resolution with Multiple-Focal-length Degradation. In Signal Processing: Image Communication.

Cuixin Yang, Jun Xiao, Cong Zhang, Kin-Man Lam (2023). Improving Robustness of Single Image Super-Resolution Models with Monte Carlo Method. In ICIP.

PDF Cite DOI

Cong Zhang, Tianshan Liu, Jun Xiao, Kin-Man Lam, Qi Wang (2023). Boosting Object Detectors via Strong-Classification Weak-Localization Pretraining in Remote Sensing Imagery. In IEEE Transactions on Instrumentation and Measurement (TIM).

PDF Cite DOI

Jun Xiao, Xinyang Jiang, Ningxin Zheng, Huan Yang, Yifan Yang, Yuqing Yang, Dongsheng Li, Kin-Man Lam (2023). Online Video Super-Resolution with Convolutional Kernel Bypass Grafts. In IEEE Transaction on Multimedia (TMM).

PDF Cite

Yakun Ju, Kin-Man Lam, Jun Xiao, Cong Zhang, Cuixin Yang, Junyu Dong (2023). Efficient Feature Fusion for Learning-based Photometric Stereo. In ICASSP.

PDF Cite DOI

Jun Xiao, Qian Ye, Rui Zhao, Kin-Man Lam, Kao Wan (2021). Self-feature Learning: An Efficient Deep Lightweight Network for Image Super-resolution. In ACM-MM.

PDF Cite

Qian Ye, Jun Xiao, Kin-Man Lam, Takayuki Okatani (2021). Progressive and Selective Fusion Network for High Dynamic Range Imaging. In ACM-MM.

PDF Cite

Jun Xiao, Tianshan Liu, Rui Zhao, Kin-Man Lam (2021). Balanced distortion and perception in single-image super-resolution based on optimal transport in wavelet domain. In Neurocomputing.

PDF Cite

Rui Zhao, Tianshan Liu, Jun Xiao, Kin-Man Lam (2021). Invertible image decolorization. In IEEE Transactions on Image Processing (TIP).

PDF Cite DOI

Jun Xiao, Wenqi Jia, Kin-Man Lam (2021). Feature redundancy mining: Deep light-weight image super-resolution model. In ICASSP.

PDF Cite DOI

Jun Xiao, Rui Zhao, Kin-Man Lam (2021). Bayesian sparse hierarchical model for image denoising. In Signal Processing:Image Communication.

PDF Cite DOI

Rui Zhao, Tianshan Liu, Jun Xiao, Kin-Man Lam (2020). Deep multi-task learning for facial expression recognition and synthesis based on selective feature sharing. In ICPR.

PDF Cite DOI

Tianshan Liu, Rui Zhao, Jun Xiao, Kin-Man Lam (2020). Progressive Motion Representation Distillation With Two-Branch Networks for Egocentric Activity Recognition. In Signal Processing Letter.

PDF Cite DOI

Jun Xiao, Rui Zhao, Shun-Cheung Lai, Wenqi Jia, Kin-Man Lam (2019). Deep Progressive Convolutional Neural Network for Blind Super-Resolution With Multiple Degradations. In ICIP.

PDF Cite DOI

Experience

 
 
 
 
 
The Hong Kong Polytechnic University
Postdoc Fellow (the research talent hub scheme)
The Hong Kong Polytechnic University
Oct 2022 – Present Hong Kong
focus on research in image/video processing, high-dimensional signal processing, and diffusion models.
 
 
 
 
 
Microsoft Research Aisa
Computer Vision Researcher in MSRA
Microsoft Research Aisa
Sep 2021 – Jan 2022 Shanghai

Responsibilities include:

  • The core member in the project ``online video restoration and enhancement system" is responsible for investigating deep spatial-temporal models (i.e., RNN, LSTM, Transformer, etc.) for real-time video processing.
  • Proposed a novel knowledge transfer method based on the optimal transport theory. The performance of the lightweight models can be improved by 0.15 dB without increasing model complexity. The proposed method can significantly accelerate the running speed by 400%.