Publications
MLPHand: Real Time Multi-View 3D Hand Mesh Reconstruction via MLP Modeling [paper] [code]
Jian Yang, Jiakun Li, Guoming Li, Zhen Shen, Huai-Yu Wu, Zhaoxin Fan(corresponding author)
European Conference on Computer Vision, ECCV 2024Human Pose Driven Object Effects Recommendation [paper][code]
Zhaoxin Fan, Fengxin Li, Hongyan Liu, Jun He, and Xiaoyong Du
2024 ACM International Conference on Multimedia Retrieval, ICMR 2024ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimation [paper]
Zhaoxin Fan, Zhenbo Song, Jian Xu, Zhicheng Wang, Kejian Wu, Hongyan Liu and Jun He
2024 ACM International Conference on Multimedia Retrieval, ICMR 2024STDG: Semi-Teacher-Student Training Paradigram for Depth-guided One-stage Scene Graph Generation [paper] [code]
Xukun Zhou, Zhenbo Song, Jun He, Hongyan Liu, Zhaoxin Fan(corresponding author)
2024 ACM International Conference on Multimedia Retrieval, ICMR 2024CoDancers: Music-Driven Coherent Group Dance Generation with Choreographic Unit [paper]
Kaixing Yang, Xukun Zhou, Xulong Tang, Ran Diao, Hongyan Liu, Jun He, Zhaoxin Fan(corresponding author)
2024 ACM International Conference on Multimedia Retrieval, ICMR 2024BeatDance: A Beat-Based Model-Agnostic Contrastive Learning Framework for Music-Dance Retrieval [paper]
Kaixing Yang, Xukun Zhou, Xulong Tang, Ran Diao, Hongyan Liu, Jun He, Zhaoxin Fan(corresponding author)
2024 ACM International Conference on Multimedia Retrieval, ICMR 2024SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis [paper][code]
Ziqiao Peng, Wentao Hu, Yue Shi, Xiangyu Zhu, Xiaomei Zhang, Hao Zhao, Jun He, Hongyan Liu, Zhaoxin Fan (corresponding author).
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2024MonoSIM: Simulating Learning Behaviors of Heterogeneous Point Cloud Object Detectors for Monocular 3D Object Detection [paper] [code]
Han Sun, Zhaoxin Fan (equal contribution), Zhenbo Song, Zhicheng Wang, Kejian Wu, and Jianfeng Lu.
IEEE Transactions on Instrumentation & Measurement, TIM 2024Everything2Motion: Synchronizing Diverse Inputs via a Unified Framework for Human Motion Synthesis[paper]
Zhaoxin Fan, Longbin Li, Pengxin Xu, Fan Shen, kai Chen.
Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024FuRPE: Learning Full-body Reconstruction from Part Experts [paper][code]
Zhaoxin Fan, Yuqing Pan, Hao Xu, Zhenbo Song, Zhicheng Wang, Kejian Wu, Hongyan Liu, and Jun He
Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024 WorkshopMulti-dimensional Fusion and Consistency for Semi-supervised Medical Image Segmentation [paper]
Yixing Lu, Zhaoxin Fan (equal contribution）, Min Xu
International Conference on Multimedia Modeling, MMM 2024A novel transformer autoencoder for multi-modal emotion recognition with incomplete data [paper]
Cheng Cheng, Wenzhe Liu, Zhaoxin Fan, Lin Feng, Ziyu Jia
Neural Networks, 2024EmoTalk: Speech-driven emotional disentanglement for 3D face animation [paper][code]
Ziqiao Peng, Haoyu Wu, Zhenbo Song, Hao Xu, Xiangyu Zhu, Hongyan Liu, Jun He, Zhaoxin Fan(corresponding author).
International Conference on Computer Vision, ICCV 2023.D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field [paper][code]
Ziqiao Peng, Haoyu Wu, Zhenbo Song, Hao Xu, Xiangyu Zhu, Hongyan Liu, Jun He, Zhaoxin Fan(corresponding author).
International Conference on Computer Vision, ICCV 2023.SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces [paper][code]
Ziqiao Peng, Yihao Luo, Yue Shi, Hao Xu, Xiangyu Zhu, Hongyan Liu, Jun He, Zhaoxin Fan(corresponding author).
ACM International Conference on Multimedia, ACM MM 2023Deep Semantic-aware Remote Sensing Image Deblurring [paper]
Zhenbo Song, Zhenyuan Zhang, Feiyi Fang, Zhaoxin Fan, Jianfeng Lu
Signal Processing, 2023.Reconstruction-Aware Prior Distillation for Semi-supervised Point Cloud Completion [paper]
Zhaoxin Fan, Yulin He, Zhicheng Wang, Kejian Wu, Hongyan Liu and Jun He
International Joint Conference on Artificial Intelligence, IJCAI 2023.Robust Single Image Reflection Removal Against Adversarial Attacks [paper]
Zhenbo Song, Zhenyuan Zhang, Kaihao Zhang, Wenhan Luo, Zhaoxin Fan, Wenqi Ren, Jianfeng Lu
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2023.GIDP: Learning a Good Initialization and Inducing Descriptor Post-enhancing for Large-scale Place Recognition [paper]
Zhaoxin Fan, Zhenbo Song, Hongyan Liu, and Jun He
International Conference on Robotics and Automation, ICRA 2023.Object Level Depth Reconstruction for Category Level 6D Object Pose Estimation From Monocular RGB Image [paper][code]
Zhaoxin Fan, Zhenbo Song, Jian Xu, Zhicheng Wang, Kejian Wu, Hongyan Liu and Jun He
European Conference on Computer Vision, ECCV 2022.RPR-Net: A Point Cloud-based Rotation-Aware Large Scale Place Recognition Network [paper]
Zhaoxin Fan, Zhenbo Song, Wenping Zhang, Hongyan Liu, Jun He, and Xiaoyong Du
European Conference on Computer Vision-the 3rd Autonomous Vehicle Vision Workshop, ECCV Workshop 2022.SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition [paper][code]
Zhaoxin Fan, Zhenbo Song, Zhiwu Lu, Hongyan Liu, Jun He, and Xiaoyong Du
36th AAAI Conference on Artificial Intelligence, AAAI 2022.Unsupervised Multi-task Learning for 3D Subtomogram Image Alignment, Clustering and Segmentation [paper]
Haoyi Zhu, Chuting Wang, Yuanxin Wang, Zhaoxin Fan, Mostofa Rafid Uddin, Xin Gao, Jing Zhang, Xiangrui Zeng and Min Xu
IEEE International Conference on Information Processing, ICIP 2022.PilotAttnNet: Multi-Modal Attention Network for End-to-End Steering Control [paper]
Jincan Zhang, Zhenbo Song, Jianfeng Lu, Xingwei Qu, Zhaoxin Fan
Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2022.Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview [paper]
Zhaoxin Fan, Yazhi Zhu, Yulin He, Qi Sun, Hongyan Liu, and Jun He
ACM Computing Surveys, CSUR 2022.SRNet: A 3D Scene Recognition Network using Static Graph and Dense Semantic Fusion [paper]
Zhaoxin Fan, Hongyan Liu, Jun He, Qi Sun, and Xiaoyong Du
Computer Graphics Forum, CGF 2020.A Graph‐based One‐Shot Learning Method for Point Cloud Recognition [paper]
Zhaoxin Fan, Hongyan Liu, Jun He, Qi Sun, and Xiaoyong Du
Computer Graphics Forum, CGF 2020.MPDNet: A 3D Missing Part Detection Network Based on Point Cloud Segmentation [paper]
Zhaoxin Fan, Hongyan Liu, Jun He, Min Zhang, and Xiaoyong Du
2021 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021.DAGC: Employing Dual Attention and Graph Convolution for Point Cloud based Place Recognition [paper]
Qi Sun, Hongyan Liu, Jun He, Zhaoxin Fan, and Xiaoyong Du
2020 ACM International Conference on Multimedia Retrieval, ICMR 2020PointFPN: A Frustum-based Feature Pyramid Network for 3D Object Detection [paper]
Zhaoxin Fan, Hongyan Liu, Jun He, Siwei Jiang, and Xiaoyong Du
2020 International Conference on Tools with Artificial Intelligence, ICTAI 2020.DenseMP: Unsupervised Dense Pre-training for Few-shot Medical Image Segmentation [paper][code]
Jason Zhaoxin Fan, Puquan Pan, Zeren Zhang, Ce Chen, Tianyang Wang, Siyang Zheng, and Min Xu.
ArxivSHLE: Devices Tracking and Depth Filtering for Stereo-based Height Limit Estimation [paper][code]
Zhaoxin Fan, Kaixing Yang, Min Zhang, Zhenbo Song, Hongyan Liu, and Jun He
Arxiv paper- Chinese National Invention Patent: 一种限高装置高度检测方法和系统. 国家发明专利. 202110986662.0.
- Chinese National Invention Patent: 一种使用单目RGB图像进行虚拟人驱动的方法. 国家发明专利. 202310607235.9.
- Chinese National Invention Patent: 一种基于情绪解耦的3D说话人驱动技术. 国家发明专利. 202311272884.1.
- Chinese National Invention Patent: 一种基于自监督语音-文本对齐的说话人唇形驱动方法. 国家发明专利. 202310839287.6.
- Chinese National Invention Patent: 一种基于 Wav2Lip 模型视频说话人的后处理方法. 国家发明专利. 202411313754.2.
- Chinese National Invention Patent: 一种基于多视角解构的单目物体深度估计与三维重建方法. 国家发明专利.
- Chinese National Invention Patent: 一种基于稀疏特征与渐进式几何扩散引导的微缩景观纹理重建方法. 国家发明专利.
- Chinese National Invention Patent: 一种基于多层注意一致性约束的高斯多视角图像生成方法. 国家发明专利.