🌇 Hi there👋🏻, I am Yunfei (☁️🪽), a senior researcher at International Digital Economy Academy (IDEA). I am now leading an effort on talking head generation, face tracking, humuan video generation, human-centric 3DGS and video content generation research. If you are seeking any form of academic cooperation, please feel free to email me at liuyunfei@idea.edu.cn.

I got my Ph.D. degree from Beihang University, advised by Prof. Feng Lu. Previously, I received my BSc degree in Computer Science from Beijing Institute of Technology in 2017.

My research aims to build multimodal, highly expressive, lifelike, and immersive interactive agents, covering perception, understanding, reconstruction, and generation of humans and the world. Specifically:

1. 🎑 Scene perception and enhancement: USI3D, SGRRN, SILS.

2. 👀 Human–environment interaction perception: PnP-GA, GazeOnce, WISWYS.

3. 😏 2D/3D Head and body reconstruction, animation, and generation: TEASER, GUAVA, GPAvatar, MODA, HRAvatar, DiffSHEG, TokenFace.

4. 🎞 Image/Video editing and generation: Qffusion, STEM-inv, AddMe.

Previously, I also worked on network interpretability AR/VR, and industrial anomaly detection: Refool, EGNIA, 3DEG, UTAD.

I serve as a reviewer for international conferences and journals, e.g., CVPR, ICCV, NeuIPS, ICLR, ICML, ACM MM, TPAMI, IJCV, PR, TVCG, etc..

👏 We are currently looking for self-motivated interns to explore cutting-edge techniques such as Gaussian Splatting and DM/FM. Feel free to contact me if you are interested. zhihu

🔥 News

• [July, 2025]:  🎉 One TVCG paper is accepted. Project and demos are coming soon.
• [July, 2025]:  🎉 I will serve as a Program Committee for AAAI 2026.
• [June, 2025]:  🎉 Two ICCV papers are accepted. Codes and demos are coming soon.
• [May, 2025]:  🎉 We introcuce GUAVA, a new Upper Body 3D Gaussian Avatar.
• [May, 2025]:  🎉 The code of HRAvatar has been released.
• [March, 2025]:  🎉 The code of TEASER has been released.
• [February, 2025]:  🎉 Our HRAvatar has been accepted to CVPR 2025.

• [Jan, 2025]:  🎉 Our TEASER has been accepted to ICLR 2025.

• [2024]: 5 papers have been accepted by ICLR, CVPR, AAAI, ECCV.

📝 Publications

📩 denotes corresponding author, 📌 denotes co-first author.

ICCV 2025

GUAVA: Generalizable Upper Body 3D Gaussian Avatar

Dongbin Zhang, Yunfei Liu📩, Lijian Lin, Ye Zhu, Yang Li, Minghan Qin, Yu Li, Haoqian Wang📩

Project | Video

• ⚡️ Reconstructs 3D upper-body Gaussian avatars from single image in 0.1s
• ⏱️ Supports real-time expressive animation and novel view synthesis at 50FPS !

CVPR 2025

HRAvatar: High-Quality and Relightable Gaussian Head Avatar

Dongbin Zhang, Yunfei Liu, Lijian Lin, Ye Zhu, Kangjie Chen, Minghan Qin, Yu Li, Haoqian Wang

Project | Code

• We propose HRAvatar, a 3D Gaussian Splatting-based method that reconstructs high-fidelity, relightable 3D head avatars from monocular videos by jointly optimizing tracking, deformation, and appearance modeling.
• By leveraging learnable blendshapes, physically-based shading, and end-to-end optimization, HRAvatar significantly improves head quality and realism under novel lighting conditions.

ICLR 2025

TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction

Yunfei Liu📌, Lei Zhu📌, Lijian Lin, Ye Zhu, Ailing Zhang, Yu Li

Project | Code

• A novel approach that achieves more accurate facial expression reconstruction by predicting a hybrid representation of faces from a single image.
• A multi-scale facial appearance tokenizer and a token-guided neural renderer to generate high-fidelity facial images. The extracted token is interpretable and highly disentangled, enabling various downstream applications.

CVPR 2024

DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation

Junming Chen, Yunfei Liu, Jianan Wang, Ailing Zeng, Yu Li, Qifeng Chen

Project

• We propose DiffSHEG, a Diffusion-based approach for Speech-driven Holistic 3D Expression and Gesture generation with arbitrary length.
• Our diffusion-based co-speech motion generation transformer enables uni-directional information flow from expression to gesture, facilitating improved matching of joint expression-gesture distributions

ICCV 2023

MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions

Yunfei Liu, Lijian Lin, Fei Yu, Changyin Zhou, Yu Li

Project

• We propose a unified system for multi-person, diverse, and high-fidelity talking portrait video generation.
• Extensive evaluations demonstrate that the proposed system produces more natural and realistic video portraits compared to previous methods.

TPAMI 2023

First- And Third-person Video Co-analysis By Learning Spatial-temporal Joint Attention

Huangyue Yu, Minjie Cai, Yunfei Liu, Feng Lu

Project | IF=17.730

• We propose a multi-branch deep network, which extracts cross-view joint attention and shared representation from static frames with spatial constraints, in a self-supervised and simultaneous manner.
• We demonstrate how the learnt joint information can benefit various applications.

CVPR 2022

GazeOnce: Real-Time Multi-Person Gaze Estimation

Mingfang Zhang, Yunfei Liu, Feng Lu

Project

• GazeOnce is the first one-stage endto-end gaze estimation method.
• This unified framework not only offers a faster speed, but also provides a lower gaze estimation error compared with other SOTA methods.

ICCV 2021

Generalizing Gaze Estimation with Outlier-guided Collaborative Adaptation

Yunfei Liu📌, Ruicong Liu📌, Haofei Wang, Feng Lu

Project

• PnP-GA is an ensemble of networks that learn collaboratively with the guidance of outliers.
• Existing gaze estimation networks can be directly plugged into PnP-GA and generalize the algorithms to new domains.

CVPR 2020

Unsupervised Learning for Intrinsic Image Decomposition from a Single Image

Yunfei Liu, Yu Li, Shaodi You, Feng Lu

Project

• USI3D is the first intrinsic image decomposition method that learns from uncorrelected image sets.
• Academic Impact: This work is included by many low-level vision projects, such as Relighting4D , IntrinsicHarmony, DIB-R++. Discussions in Zhihu.

ECCV 2020

Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks

Yunfei Liu, Xingju Ma, James Bailey, Feng Lu

[Project | (Citations 750+)]

• We present a new type of backdoor attack: natural reflection phenomenon.
• Academic Impact: This work is included by many backdoor attack/defense works, Such as NAD . This work is at the first place at google scholar .

• TVCG 2025 Qffusion: Controllable Portrait Video Editing via Quadrant-Grid Attention Learning, Maomao Li, Lijian Lin, Yunfei Liu📩, Ye Zhu, Yu Li

• ICCV 2025 CanonSwap: High-Fidelity and Consistent Video Face Swapping via Canonical Space Modulation, Xiangyang Luo,  Ye Zhu,  Yunfei Liu, Lijian Lin,  Cong Wan,  Zijian Cai, Shao-Lun Huang, Yu Li
• AAAI 2025 AnyTalk: Multi-modal Driven Multi-domain Talking Head Generation, Yu Wang, Yunfei Liu, Fa-Ting Hong, Meng Cao, Lijian Lin, Yu Li
• ECCV 2024 AddMe: Zero-shot Group-photo Synthesis by Inserting People into Scenes, Dongxu Yue, Maomao Li, Yunfei Liu, Ailing Zeng, Tianyu Yang, Qin Guo, Yu Li
• CVPR 2024 A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing, Maomao Li, Yu Li, Tianyu Yang, Yunfei Liu, Dongxu Yue, Zhihui Lin, Dong Xu
• ICLR 2024 GPAvatar: Generalizable and Precise Head Avatar from Image(s), Xuangeng Chu, Yu Li, Ailing Zeng, Tianyu Yang, Lijian Lin, Yunfei Liu, Tatsuya Harada
• PRCV 2024 Visibility Enhancement for Low-light Hazy Scenarios, Chaoqun Zhuang, Yunfei Liu, Sijia Wen, Feng Lu.
• ICCV 2023 Accurate 3D Face Reconstruction with Facial Component Tokens, Tianke Zhang, Xuangeng Chu, Yunfei Liu, Lijian Lin, Zhendong Yang, et al..
• CVMJ 2023 Discriminative feature encoding for intrinsic image decomposition, Zhongji Wang, Yunfei Liu, Feng Lu.
• CVPR 2022 Generalizing Gaze Estimation with Rotation Consistency, Yiwei Bao, Yunfei Liu, Haofei Wang, Feng Lu.
• IEEE-VR 2022 Reconstructing 3D Virtual Face with Eye Gaze from a Single Image, Jiadong Liang, Yunfei Liu, Feng Lu. [Oral]
• TOMM 2022 Semantic Guided Single Image Reflection Removal, Yunfei Liu, Yu Li, Shaodi You, Feng Lu, GitHub.
• arXiv 2022 Jitter Does Matter: Adapting Gaze Estimation to New Domains, Mingjie Xu, Haofei Wang, Yunfei Liu, Feng Lu.
• ISAMR 2021 3D Photography with One-shot Portrait Relighting, Yunfei Liu, Sijia Wen, Feng Lu.
• ISAMR 2021 Edge-Guided Near-Eye Image Analysis for Head Mounted Displays, Zhimin Wang*, Yuxin Zhao*, Yunfei Liu, Feng Lu. [Oral] GitHub, Demo video
• BMVC 2021 Separating Content and Style for Unsupervised Image-to-Image Translation, Yunfei Liu, Haofei Wang, Yang Yue, Feng Lu. GitHub.
• arXiv 2021 Unsupervised Two-Stage Anomaly Detection, Yunfei Liu, Chaoqun Zhuang, Feng Lu, GitHub.
• arXiv 2021 Cloud Sphere: A 3D Shape Representation via Progressive Deformation, Zongji Wang, Yunfei Liu, Feng Lu.
• arXiv 2021 Vulnerability of Appearance-based Gaze Estimation, Mingjie Xu, Haofei Wang, Yunfei Liu, Feng Lu.
• AAAI 2020 Separate In Latent Space: Unsupervised Single Image Layer Separation, Yunfei Liu, Feng Lu. GitHub [Oral]
• ICPR 2020 Adaptive Feature Fusion Network for Gaze Tracking in Mobile Tablets, Yiwei Bao, Yihua Cheng, Yunfei Liu, Feng Lu. GitHub.
• ACM-MM 2019 What I See Is What You See: Joint Attention Learning for First and Third Person Video Co-analysis, Huangyue Yu, Minjie Cai, Yunfei Liu, Feng Lu.

🎖 Honors and Awards

• Shenzhen Artificial Intelligence Natural Science Award, 2023

• Shenzhen Pengcheng special talent award, 2023

ICCV 2019 Workshop

Winner of Hyperspectral City Challenge 1.0, Rank: 1.

Yunfei Liu

Project

• Adopt adopts multi-channel multi-spectum data to guide semantic segmentation for cityscapes.

CADC 2015

Vertical Take-Off and Landing (VTOL) track. First prize

Yunfei Liu, Changjing Wang, Chao Ma, Haonan Zheng, Yongzhen Pan.

Project

• China Aeromodelling Design Challenge. Vertical Take-Off and Landing (VTOL) track. First prize, Rank: 6/70.

• 2021.10 National Scholarship.
• 2021.11 Principal scholarship.

📖 Educations

• 2017.09 - 2022.11, Beihang University, School of Computer Science and Engineering, State Key Labratory of Virtual Reality Technology and Systems.
• 2013.08 - 2017.06, Beijing Insitute of Technology, School of Computer Science and Technology.

💬 Invited Talks

• 2021.06, Visual intelligence for enhanced perception, Huawei internal talk
• 2021.06, Digital Image Processing, Beihang international class
• 2020.06, Deep learning interpretability, Meituan internal talk

💻 Internships

• 2022.03 - 2022.10, IDEA, Vistring Lab, Shenzhen, China.
• 2016.07 - 2017.05, DJI, Visual Perception Group, Shenzhen, China.