Lingteng Qiu    邱陵腾

Email       Google Scholar      Github

I graduated in October 2024 and joined Alibaba's Tongyi Lab. Prior to that, I had been a Ph.D. student (since September 2020) at the School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, under the supervision of Prof. Xiaoguang Han. Before my time at CUHK-Shenzhen, I earned my M.S. from the Department of Automation at Harbin Institute of Technology and my B.S. from Fuzhou University. I am fortunate to have worked closely with Prof. Guanying Chen at SYSU-Sz.


My research interests are in computer vision, computer graphics, and machine learning, specifically in the realm of creating high-quality, animatable 3D avatars using AI.

profile photo
News

2024-07: Two papers got accepted by SIGGRAPH-Asia (TOG), more details comming soon!
2024-07: Two papers got accepted by ECCV2024, more details comming soon!
2024-04: Two papers were selected as Highlight (2.8%) by CVPR2024!
2024-02: Three paper got accepted by CVPR 2024!
2023-02: One paper got accepted by CVPR 2023!
2022-03: Two papers got accepted by CVPR 2022!
2021-03: One paper got accepted by CVPR 2021!
2020-07: One paper got accepted by ECCV 2020! Code and dataset are available.

Research Highlight

CVPR2024: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D

CVPR2022: Towards High-Fidelity Garment mesh Reconstruction from Single Images

CVPR2023: REconstructing 3D Dynamic Cloth from Monocular Videos

ECCV2020: Peeking into Occluded Joints, A Novel Framework for Crowd Pose Estimation

Preprints (# corresponding author, * equal contribution)
VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model
Qi Zuo*, Xiaodong Gu*, Lingteng Qiu, Yuan Dong, Zhengyi Zhao, Weihao Yuan, Rui Peng,
Siyu Zhu, Zilong Dong, Liefeng Bo, Qixing Huang
arXiv preprint.
[PDF] [Project] [Code]
SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Scene Segmentation
Mutian Xu, Xingyilang Yin, Lingteng Qiu, Yang liu, Xin Tong, Xiaoguang Han
arXiv preprint.
[PDF] [Project] [Code]
Publications (# corresponding author, * equal contribution, + project leader)
StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal
Chongjie Ye* Lingteng Qiu*, Xiaodong Gu, Qi Zuo, Yushuang Wu, Zilong Dong, Liefeng Bo, Yuliang Xiu#, Xiaoguang Han#
ACM Transaction on Graphics (TOG), Proceedings of ACM SIGGRAPH Asia 2024

[PDF] [Project] [Code]
RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D
Lingteng Qiu*, Guanying Chen*, Xiaodong Gu*, Qi Zuo, Mutian Xu, Yushuang Wu, Weihao Yuan, Zilong Dong, Liefeng Bo, Xiaoguang Han
IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Highlight
[PDF] [Project] [Code]
IPoD: Implicit Field Learning with Point Diffusion for Generalizable 3D Object Reconstruction from Single RGB-D Images
Yushuang Wu, Luyue Shi, Junhao Cai, Weihao Yuan, Lingteng Qiu, Zilong Dong, Liefeng Bo, Shuguang Cui, Xiaoguang Han
IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Highlight
[PDF] [Project] [Code]
MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures
Zhangyang Xiong*, Chenghong Li*, Kenkun Liu*, Hongjie Liao, Jianqiao Hu, Junyi Zhu,
Shuliang Ning, Lingteng Qiu, Chongjie Wang, Shijie Wang, Shuguang Cui, Xiaoguang Han
IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024
[PDF] [Project] [Dataset] [Code]
REC-MV: REconstructing 3D Dynamic Cloth from Monocular Videos
Lingteng Qiu*, Guanying Chen*, Jiapeng Zhou, MutianXu, Junle Wang, Xiaoguang Han#
IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
[Project] [PDF] [BibTeX] [Code]

ETHSeg: An Amodel Instance Segmentation Network and a Real-world Dataset for X-Ray Waste Inspection
Lingteng Qiu, Zhangyang Xiong, Xuhao Wang, KenKun Liu, Guanying Chen, Xiaoguang Han#, Shuguang Cui
IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
[Project] [PDF] [Dataset] [BibTeX]

Registering Explicit to Implicit: Towards High-Fidelity Garment mesh Reconstruction from Single Images
Heming Zhu, Lingteng Qiu, Yuda Qiu, Xiaoguang Han#
IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
[Project] [PDF] [BibTeX] [Code]

3DCaricShop: A Dataset and A Baseline Method for Single-view 3D Caricature Face Reconstruction
Yuda Qiu, Xiaojie Xu, Lingteng Qiu, Yan Pan, Yushuang Wu, Weikai Chen, Xiaoguang Han#
IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
[Project] [PDF] [Dataset] [BibTeX] [Code]

Peeking into Occluded Joints: A Novel Framework for Crowd Pose Estimation
Lingteng Qiu, Yanran Li, Guanbin Li ,Xiaojun Wu, Zixiang Xiong, Xiaoguang Han#, Shuguang Cui
European Conference on Computer Vision, ECCV 2020
[Project] [PDF] [BibTeX] [Code]

Projects
Open-PIFuhd
This is an implementation of PIFuhd based on PyTorch, including rendering image normal map, training both coarse-PIFu and fine-PIFu.
[Code]


DeeperLab
This project aims at providing a fast, modular reference implementation for semantic segmentation models using PyTorch.
[Code]


Talks
REC-MV: REconstructing 3D Dynamic Cloth from Monucular Videos
Invited by Dr. Yi Zhou
Digital Humans Seminar, Adobe, 2023
[PPT Download]


Current Collaborators
Guanying Chen, Associate Professor at SYSU, Shenzhen
Mutian Xu, Ph.D student at CUHK-SZ
Xiaodong Gu, Technical Expert at Alibaba-Inc

The website template was adapted from Jon Barron.