📝 Publications
ICCV 2023
MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions
Yunfei Liu, Lijian Lin, Fei Yu, Changyin Zhou, Yu Li
- 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
- 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
- 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
- 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 300+)]
- 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 .
ICCV 2023Accurate 3D Face Reconstruction with Facial Component Tokens, Tianke Zhang, Xuangeng Chu, Yunfei Liu, Lijian Lin, Zhendong Yang, et al..arXiv 2023Visibility Enhancement for Low-light Hazy Scenarios, Chaoqun Zhuang, Yunfei Liu, Sijia Wen, Feng Lu.CVMJ 2023Discriminative feature encoding for intrinsic image decomposition, Zhongji Wang, Yunfei Liu, Feng Lu.CVPR 2022Generalizing Gaze Estimation with Rotation Consistency, Yiwei Bao, Yunfei Liu, Haofei Wang, Feng Lu.IEEE-VR 2022Reconstructing 3D Virtual Face with Eye Gaze from a Single Image, Jiadong Liang, Yunfei Liu, Feng Lu. [Oral]TOMM 2022Semantic Guided Single Image Reflection Removal, Yunfei Liu, Yu Li, Shaodi You, Feng Lu, GitHub.arXiv 2022Jitter Does Matter: Adapting Gaze Estimation to New Domains, Mingjie Xu, Haofei Wang, Yunfei Liu, Feng Lu.ISAMR 20213D Photography with One-shot Portrait Relighting, Yunfei Liu, Sijia Wen, Feng Lu.ISAMR 2021Edge-Guided Near-Eye Image Analysis for Head Mounted Displays, Zhimin Wang*, Yuxin Zhao*, Yunfei Liu, Feng Lu. [Oral] GitHub, Demo videoBMVC 2021Separating Content and Style for Unsupervised Image-to-Image Translation, Yunfei Liu, Haofei Wang, Yang Yue, Feng Lu. GitHub.arXiv 2021Unsupervised Two-Stage Anomaly Detection, Yunfei Liu, Chaoqun Zhuang, Feng Lu, GitHub.arXiv 2021Cloud Sphere: A 3D Shape Representation via Progressive Deformation, Zongji Wang, Yunfei Liu, Feng Lu.arXiv 2021Vulnerability of Appearance-based Gaze Estimation, Mingjie Xu, Haofei Wang, Yunfei Liu, Feng Lu.AAAI 2020Separate In Latent Space: Unsupervised Single Image Layer Separation, Yunfei Liu, Feng Lu. GitHub [Oral]ICPR 2020Adaptive Feature Fusion Network for Gaze Tracking in Mobile Tablets, Yiwei Bao, Yihua Cheng, Yunfei Liu, Feng Lu. GitHub.ACM-MM 2019What 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.