Xi Zhang

I am currently a Research Scientist in the Alibaba-NTU Global e-Sustainability CorpLab (ANGEL) at Nanyang Technological University (NTU), working with Prof Weisi Lin. Before that, I was a postdoctoral fellow at McMaster University (Mac), Canada from July 2022 to August 2024, supervised by Prof Xiaolin Wu. I was also an assistant researcher at Department of Electronic Engineering, Shanghai Jiao Tong University (SJTU), supervised by Prof Hongkai Xiong. I earned my PhD from SJTU in June 2022 and my bachelor’s degree in Mathematics and Physics Basic Science from UESTC in 2015.

My current research interests focus on green and energy-efficient AI technologies that prioritize sustainable ecosystems and lifestyles. Previously, I concentrated on learning-based data compression techniques, particularly for visual data such as images, videos, point clouds, and light fields. Additionally, I am also interested in core deep learning challenges, including domain generalization and visual reasoning. I have published more than 10 papers at the top AI Journals and conferences such as T-PAMI, T-IP, NeurIPS, CVPR, ECCV, AAAI, etc.

News

Apr 05, 2025	🔥 Our CVPR 2025 paper has been selected as a highlight (Top 3%).
Feb 26, 2025	🎉 One paper on multirate image compression is accepted by CVPR 2025.
Sep 30, 2024	🎉 One paper on optimal lattice vector quantizer is accepted by NeurIPS 2024.
Jul 25, 2024	🎉 One paper on point cloud compression is accepted by ECCV 2024.
Jan 28, 2024	🎉 One paper on light field image compression is accepted by JVCI.
Mar 10, 2023	🎉 One paper on LVQ for image compression is accepted by CVPR 2023.

Selected Publications

CVPR 2025 - Highlight

Multirate Neural Image Compression with Adaptive Lattice Vector Quantization

Hao Xu, Xiaolin Wu, and Xi Zhang

IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Abs Bib HTML

@inproceedings{xu2025multirate,
  title = {Multirate Neural Image Compression with Adaptive Lattice Vector Quantization},
  author = {Xu, Hao and Wu, Xiaolin and Zhang, Xi},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {},
  year = {2025},
}

NeurIPS 2024

Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression

Xi Zhang, and Xiaolin Wu

Advances in Neural Information Processing Systems, 2024

Abs Bib HTML

@inproceedings{zhang2024learning,
  title = {Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression},
  author = {Zhang, Xi and Wu, Xiaolin},
  booktitle = {Advances in Neural Information Processing Systems},
  volume = {37},
  year = {2024},
}

ECCV 2024

Fast Point Cloud Geometry Compression with Context-Based Residual Coding and INR-Based Refinement

Hao Xu, Xi Zhang, and Xiaolin Wu

European Conference on Computer Vision, 2024

Abs Bib HTML

@inproceedings{xu2024fast,
  title = {Fast Point Cloud Geometry Compression with Context-Based Residual Coding and INR-Based Refinement},
  author = {Xu, Hao and Zhang, Xi and Wu, Xiaolin},
  booktitle = {European Conference on Computer Vision},
  pages = {270--288},
  year = {2024},
  organization = {Springer},
}

JVCI 2024

Low-complexity ℓ∞-compression of light field images with a deep-decompression stage

M Umair Mukati, Xi Zhang, Xiaolin Wu, and Søren Forchhammer

Journal of Visual Communication and Image Representation, 2024

Abs Bib HTML

@article{mukati2024low,
  title = {Low-complexity ℓ∞-compression of light field images with a deep-decompression stage},
  author = {Mukati, M Umair and Zhang, Xi and Wu, Xiaolin and Forchhammer, S{\o}ren},
  journal = {Journal of Visual Communication and Image Representation},
  volume = {99},
  pages = {104072},
  year = {2024},
  publisher = {Elsevier},
}

CVPR 2023

Lvqac: Lattice vector quantization coupled with spatially adaptive companding for efficient learned image compression

Xi Zhang, and Xiaolin Wu

IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Abs Bib HTML

@inproceedings{zhang2023lvqac,
  title = {Lvqac: Lattice vector quantization coupled with spatially adaptive companding for efficient learned image compression},
  author = {Zhang, Xi and Wu, Xiaolin},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {10239--10248},
  year = {2023},
}

TPAMI 2022

Multi-modality deep restoration of extremely compressed face videos

Xi Zhang, and Xiaolin Wu

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022

Abs Bib HTML

@article{zhang2022multi,
  title = {Multi-modality deep restoration of extremely compressed face videos},
  author = {Zhang, Xi and Wu, Xiaolin},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume = {45},
  number = {2},
  pages = {2024--2037},
  year = {2022},
  publisher = {IEEE},
}

CVPR 2021

Attention-guided image compression by deep reconstruction of compressive sensed saliency skeleton

Xi Zhang, and Xiaolin Wu

IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021

Abs Bib HTML

@inproceedings{zhang2021attention,
  title = {Attention-guided image compression by deep reconstruction of compressive sensed saliency skeleton},
  author = {Zhang, Xi and Wu, Xiaolin},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {13354--13364},
  year = {2021},
}

TIP 2021

Ultra high fidelity deep image decompression with l∞-constrained compression

Xi Zhang, and Xiaolin Wu

IEEE Transactions on Image Processing, 2021

Abs Bib HTML

@article{zhang2020ultra,
  title = {Ultra high fidelity deep image decompression with l∞-constrained compression},
  author = {Zhang, Xi and Wu, Xiaolin},
  journal = {IEEE Transactions on Image Processing},
  volume = {30},
  pages = {963--975},
  year = {2021},
  publisher = {IEEE},
}

NeurIPS 2020

On numerosity of deep neural networks

Xi Zhang, and Xiaolin Wu

Advances in Neural Information Processing Systems, 2020

Abs Bib HTML

@inproceedings{zhang2020numerosity,
  title = {On numerosity of deep neural networks},
  author = {Zhang, Xi and Wu, Xiaolin},
  booktitle = {Advances in Neural Information Processing Systems},
  volume = {33},
  pages = {1820--1829},
  year = {2020},
}

CVPR 2020 - Oral

Davd-net: Deep audio-aided video decompression of talking heads

Xi Zhang, Xiaolin Wu, Xinliang Zhai, Xianye Ben, and Chengjie Tu

IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Abs Bib HTML

@inproceedings{zhang2020davd,
  title = {Davd-net: Deep audio-aided video decompression of talking heads},
  author = {Zhang, Xi and Wu, Xiaolin and Zhai, Xinliang and Ben, Xianye and Tu, Chengjie},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {12335--12344},
  year = {2020},
}

ACM MM 2020

Deep multi-modality soft-decoding of very low bit-rate face videos

Yanhui Guo, Xi Zhang, and Xiaolin Wu

ACM International Conference on Multimedia, 2020

Abs Bib HTML

@inproceedings{guo2020deep,
  title = {Deep multi-modality soft-decoding of very low bit-rate face videos},
  author = {Guo, Yanhui and Zhang, Xi and Wu, Xiaolin},
  booktitle = {ACM International Conference on Multimedia},
  pages = {3947--3955},
  year = {2020},
}

AAAI 2019 - Spotlight

Cognitive deficit of deep learning in numerosity

Xi Zhang, Xiaolin Wu, and Xiao Shu

AAAI conference on artificial intelligence, 2019

Abs Bib HTML

@inproceedings{wu2019cognitive,
  title = {Cognitive deficit of deep learning in numerosity},
  author = {Zhang, Xi and Wu, Xiaolin and Shu, Xiao},
  booktitle = {AAAI conference on artificial intelligence},
  volume = {33},
  number = {01},
  pages = {1303--1310},
  year = {2019},
}