Xin Cai (蔡昕)

I am a third-year Ph.D. student in Information Engineering at the Multimedia Laboratory (MMLab), The Chinese University of Hong Kong, advised by Prof. Tianfan Xue.

I received my B.S. in Computer Science and Technology from the University of Chinese Academy of Sciences (UCAS) in 2020, and my M.Eng. in Applied Computer Technology from UCAS in 2023, supervised by Prof. Shiguang Shan.

My research interests include generative models (controllable editing and generation,inverse problems with generative models), computational imaging and photography (image reconstruction, image and video processing), 3D computer vision (3D reconstruction, rendering and generation), and applied computer vision techniques such as gaze estimation and emotion recognition.

CV / Google Scholar / Github
Email: caixin [at] link.cuhk.edu.hk

News

[2025.11]    End of my internship at Adobe — heartfelt thanks to all the teams!
[2025.11]    One paper to appear in TIP.
[2025.11]    One paper to appear in 3DV 2026.
[2025.06]    UltraFusion selected as Best Demo Honorable Mention @ CVPR 2025!
[2025.02]    Two papers to appear in CVPR 2025 (One Highlight).
[2024.09]    Our paper on lensless imaging has been accepted as a Spotlight at NeurIPS 2024!
[2024.09]    End of my internship at Adobe — heartfelt thanks to all the teams!
[2023.04]    Welcome to my homepage!

[Show More]

Publications

*: Equal Contribution, †: Corresponding Author

	DA-VAE: Plug-in Latent Compression for Diffusion via Detail Alignment Xin Cai, Zhiyuan You, Zhoutong Zhang, Tianfan Xue Under review, 2025 paper
	Parallax Portrait Matting Xin Cai, Jiawen Chen, Lars Jebe, Tianfan Xue, Zhoutong Zhang Under review, 2025 paper
	PhoCoLens: Photorealistic and Consistent Reconstruction in Lensless Imaging Xin Cai, Zhiyuan You, Hailong Zhang, Wentao Liu, Jinwei Gu, Tianfan Xue Neural Information Processing Systems (NeurIPS), 2024, Spotlight paper / project page / code
	LenslessFace: An End-to-End Optimized Lensless System for Privacy-Preserving Face Verification Xin Cai, Hailong Zhang, Chenchen Wang, Wentao Liu, Jinwei Gu, Tianfan Xue IEEE Transactions on Image Processing (TIP) submission, 2024 paper / project page / code
	Source-free Adaptive Gaze Estimation with Uncertainty Reduction Xin Cai, Jiabei Zeng, Shiguang Shan, Xilin Chen IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023 paper / code
	Landmark-aware Self-supervised Eye Semantic Segmentation Xin Cai, Jiabei Zeng, Shiguang Shan IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2021 paper
	Gaze Estimation with an Ensemble of Four Architectures Xin Cai, Boyu Chen, Jiabei Zeng, Jiajun Zhang, Yunjia Sun, Xiao Wang, Zhilong Ji, Xiao Liu, Xilin Chen, Shiguang Shan arXiv preprint arXiv:2107.01980, 2021. (Technical report for the 🏆 winner solution in ETH-XGaze Gaze Estimation Challenge@CVPR 2021) paper / code

	Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution Zhiyuan You, Xin Cai, Jinjin Gu, Tianfan Xue, Chao Dong IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025 paper / project page / code / data
	UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion Zixuan Chen, Yujin Wang, Xin Cai, Zhiyuan You, Zheming Lu, Fan Zhang, Shi Guo, Tianfan Xue IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, Highlight, Best Demo Honorable Mention paper / project page / github page / code / demo (HuggingFace / OpenXLab)
	Descriptive Image Quality Assessment in the Wild Zhiyuan You, Jinjin Gu, Xin Cai, Zheyuan Li, Kaiwen Zhu, Chao Dong, Tianfan Xue IEEE Transactions on Image Processing (TIP), 2025 paper / project page / code / data
	FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution Junhao Zhuang, Shi Guo, Xin Cai, Xiaohui Li, Yihao Liu, Chun Yuan, Tianfan Xue arXiv:2510.12747, 2025 paper / project page / code / data
	LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning Chenjian Gao, Lihe Ding, Xin Cai, Zhanpeng Huang, Zibin Wang, Tianfan Xue arXiv:2506.10082, 2025 paper / project page / code
	PhotoFramer: Multi-modal Image Composition Instruction Zhiyuan You, Ke Wang, He Zhang, Xin Cai, Jinjin Gu, Tianfan Xue, Chao Dong, Zhoutong Zhang arXiv:2512.00993, 2025 paper / project page
	Collaborative Contrastive Learning for Cross-domain Gaze Estimation Lifan Xia, Yong Li, Xin Cai, Zhen Cui, Chunyan Xu, Antoni B. Chan Pattern Recognition 161:111244, 2025 paper
	DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flow Ken Deng, Yuanchen Guo, Jingxiang Sun, Zixin Zou, Yangguang Li, Xin Cai, Yanpei Cao, Yebin Liu, Ding Liang 3DV, 2025 paper

Experience

	Research Scientist Intern @ Adobe Research, San Jose, CA, USA Jun. 2025 - Nov. 2025 Topic: high compression ratio image tokenizer for generation. Worked with Zhoutong Zhang.
	Research Scientist Intern @ Adobe Nextcam, San Jose, CA, USA Jun. 2024 - Sep. 2024 Topic: mobile burst matting from the fusion of parallax cues. Worked with Marc Levoy's computational photography team.
	Ph.D. Candidate @ Multimedia Laboratory (MMLab), The Chinese University of Hong Kong Sep. 2023 - Present Topic: generative model for inverse imaging problems. Worked with Prof. Tianfan Xue.
	M.Eng. in Applied Computer Technology @ University of Chinese Academy of Sciences (UCAS) 2020 - 2023 Supervisor: Prof. Shiguang Shan
	B.S. in Computer Science and Technology @ University of Chinese Academy of Sciences (UCAS) 2016 - 2020 Cumulative GPA: 3.90/4.00 Rank: 2/69

Services

• Conference Reviewer

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Conference on Neural Information Processing Systems (NeurIPS)
International Conference on Learning Representations (ICLR)
Association for the Advancement of Artificial Intelligence (AAAI)
International Conference on Machine Learning (ICML)
IEEE/CVF International Conference on Computer Vision (ICCV)

• Journal Reviewer

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
IEEE Transactions on Image Processing (TIP)
IEEE Transactions on Computational Imaging (TCI)
Computer Vision and Image Understanding (CVIU)

Awards

    Academy Scholarship, University of Chinese Academy of Sciences, 2017, 2018, 2019
    Tang Lixin Academic Excellence Scholarship, Jun. 2020
    1st Prize, ETH-XGaze Challenge, Jun. 2021
    Merit Student, University of Chinese Academy of Sciences, 2018, 2021, 2023
    Postgraduate Studentship, Mar. 2023
    Outstanding Tutors Award, 2024

Template inspired by Jon Barron and Zhiyuan You.