About
I’m a Research Scientist in the Learning and Perception Research team at NVIDIA Research. I received my Ph.D. in the Department of Computer Science at Shanghai Jiao Tong University (SJTU) in 2024. I was a member of SJTU MVIG lab under the supervision of Prof.Cewu Lu. Prior to that, I received my Bachelor degree (Electronic Engineering) in 2018 and Master degree (Computer Science) in 2020 from Shanghai Jiao Tong University. My research interests mainly lies in reconstruction, modeling and animation of Digital Human.
News
[2024/07] Join NVIDIA Research as a Research Scientist.
[2024/05] Defend my Ph.D. thesis.
[2023/06] Start my internship at NVIDIA Research.
[2023/02] Our paper NIKI is accepted in CVPR2023.
[2022/12] Tech Talk about AlphaPose at TechBeat.
[2022/11] AlphaPose is accepted by TPAMI!
------ More/Less ------
[2022/10] I am invited to give a talk at IDEA.
[2022/09] Jittor version of AlphaPose is released!
[2022/07] Our paper D&D is accepted in ECCV2022 (Oral).
[2022/07] Our paper SmoothNet and DLSA are accepted in ECCV2022.
[2022/06] 吴班 Talk: Regression From the Perspective of MLE (Link).
[2022/04] New DEMO code and colab 
for HybrIK are available.
[2021/09] Our paper Sampling-Argmax is accepted in NeurIPS2021.
[2021/09] Invited Talk at Max-Planck Institute, Perceiving Systems Department.
[2021/07] CVPR 2021特别企划: 基于混合逆运动学解法的3D人体形态估计 (Video).
[2021/07] Our paper Residual Log-likelihood Estimation is accepted in ICCV2021 (Oral).
[2021/07] Our paper CPF is accepted in ICCV2021.
[2021/03] Our paper HybrIK is accepted in CVPR2021.
[2020/05] Our paper HMOR is accepted in ECCV2020 (Spotlight).
[2020/02] Our paper 2D-3D Joint HOI Learning is accepted in CVPR2020.
[2019/07] AlphaPose is included in GluonCV model zoo now.
[2019/02] Our Paper CrowdPose is accepted in CVPR2019 (Oral).
[2018/12] Our CrowdPose dataset is available!
[2018/09] PyTorch version of AlphaPose is released!
[2018/07] Our paper PoseFlow is accepted in BMVC2018.
[2018/02] Our real-time accurate multi-person pose estimation system AlphaPose is released!
Projects
Publications
COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimation
Jiefeng Li, Ye Yuan, Davis Rempe, Haotian Zhang, Pavlo Molchanov, Cewu Lu, Jan Kautz, and Umar IqbalECCV 2024
[Paper]
Denoising Vision Transformer
Jiawei Yang*, Katie Z Luo*, Jiefeng Li, Kilian Q Weinberger, Yonglong Tian, and Yue Wang(*=equal contribution)
ECCV 2024
[Paper][Project Page][Code]
NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation
Jiefeng Li*, Siyuan Bian*, Qi Liu, Jiasheng Tang, Fan Wang, and Cewu Lu(*=equal contribution)
AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time
Hao-Shu Fang*, Jiefeng Li*, Hongyang Tang, Chao Xu, Haoyi Zhu, Yuliang Xiu, Yong-Lu Li and Cewu Lu(*=equal contribution)
D&D: Learning Human Dynamics from Dynamic Camera
Jiefeng Li, Siyuan Bian, Chao Xu, Gang Liu, Gang Yu and Cewu Lu
Localization with Sampling-Argmax
Jiefeng Li, Tong Chen, Ruiqi Shi, Yujing Lou, Yong-Lu Li and Cewu LuNeurIPS 2021
[Paper][Project Page][Code][知乎]
Human Pose Regression with Residual Log-likelihood Estimation
Jiefeng Li, Siyuan Bian, Ailing Zeng, Can Wang, Bo Pang and Cewu LuICCV 2021 (Oral presentation - Top 3%)
[Paper][Project Page][Code][知乎]
HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation
Jiefeng Li, Chao Xu, Zhicun Chen, Siyuan Bian, Lixin Yang and Cewu LuCVPR 2021
[Paper][Project Page][Code][知乎]
HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation
Jiefeng Li*, Can Wang*, Wentao Liu, Chen Qian and Cewu Lu(*=equal contribution)
ECCV 2020 (Spotlight - Top 5%)
[Paper]
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark
Jiefeng Li, Can Wang, Hao Zhu, Yihuan Mao, Hao-Shu Fang and Cewu LuCVPR 2019 (Oral presentation - Top 5.6%)
[Paper][Dataset][News][Code]
Pose Flow: Efficient Online Pose Tracking
Yuliang Xiu*, Jiefeng Li*, Haoyu Wang, Yinghong Fang and Cewu Lu
SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos
Ailing Zeng, Lei Yang, Xuan Ju, Jiefeng Li, Jianyi Wang, and Qiang Xu
Constructing Balance from Imbalance for Long-tailed Image Recognition
Yue Xu*, Yong-Lu Li*, Jiefeng Li and Cewu Lu
ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis
Lixin Yang*, Kailin Li*, Xinyu Zhan, Jun Lv, Wenqiang Xu, Jiefeng Li and Cewu Lu
Unified and Fast Human Trajectory Prediction Via Conditionally Parameterized Normalizing Flow
Jianhua Sun, Zehao Wang, Jiefeng Li and Cewu LuRA-L and ICRA 2022
[Paper]
Correlation Field for Boosting 3D Object Detection in Structured Scenes
Jianhua Sun, Hao-Shu Fang, Xianghui Zhu, Jiefeng Li and Cewu LuAAAI 2022
[Paper]
Unsupervised Representation for Semantic Segmentation by Implicit Cycle-Attention Contrastive Learning
Bo Pang, Yizhuo Li, Yifan Zhang, Gao Peng, Jiajun Tang, Kaiwen Zha, Jiefeng Li and Cewu LuAAAI 2022
[Paper]
CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction
Lixin Yang, Xinyu Zhan, Kailin Li, Wenqiang Xu, Jiefeng Li and Cewu Lu
TDAF: Top-Down Attention Framework for Vision Tasks
Bo Pang, YiZhuo Li, Jiefeng Li, Muchen Li, Hanwen Cao and Cewu LuAAAI 2020
[Paper]
Detailed 2D-3D Joint Representation for Human-Object Interaction
Yong-Lu Li, Xinpeng Liu, Han Lu, Shiyi Wang, Junqi Liu, Jiefeng Li and Cewu LuCVPR 2020
[Paper][Benchmark][Slides][Code]
Talks
- Body Mesh Recovery with Inverse Kinematics – A new paradigm
- ZongMu Technology, 2023.04.03
- TechBeat: 多人场景，全身136关键点检测与跟踪框架AlphaPose技术讲解 (Link), 2022.12.28
- From skeleton to body: Robust Human Pose Estimation
- International Digital Economy Academy (IDEA), hosted by Ailing Zeng, 2022.10.19
- Regression From the Perspective of MLE | 吴班 Talk (Link), 2022.06.06
- From skeleton to body: Keypoint Estimation is Helpful for Human Body Reconstruction (Link)
- Max-Planck Institute for Intelligent Systems, Perceiving Systems Department, hosted by Yuliang Xiu, 2021.09.06
- Human Pose Regression with Residual Log-likelihood Estimation
- Tencent GY-Lab (光影实验室), hosted by Gang Yu, 2021.09.02
- Valse 2022, Workshop: 可解释的深度学习算法与视觉应用, 2022.08.24
- HybrIK: 基于混合逆运动学解法的3D人体形态估计 | CVPR 2021特别企划 (Video), 2021.07.28
Services
- Reviewer of NeurIPS’21, 22, CVPR’22, 23, ICCV’23, ECCV’22, IROS’22, IJCV, TIP, T-ASE, JVIS, etc.