|
Liting Wen Hi there 👋 ! I'm a second-year Master's student in Computer Vision (MSCV) at the Robotics Institute, Carnegie Mellon University, advised by Prof. László A. Jeni. I'm also a member of AnySyn3D, a nonprofit research group for 3D vision, advised by Prof. Xiao-Xiao Long. Email / Google Scholar / Github / Linkedin / Gallery |
|
|
My research interest lies in 3D Computer Vision, particularly including human-object interaction, human motion recovery, 3D reconstruction, as well as their applications in mixed reality and robotics. |
|
Liting Wen, Xin Lv, Jungbin Cho, László Jeni, Cheng Lin, Wenping Wang, Xiao-Xiao Long
under review
paper /
Robust & efficient monocular Hand-Object Interaction (HOI) reconstruction via discrete pose hypothesis search and a 3D relative offset prior. |
|
Yiwen Zhao, Ce Zheng, Yufu Wang, Daniel Yang, Liting Wen, László A. Jeni
CVPR, 2026
project page / paper / code
An online framework that recovers 3D human meshes and world-grounded camera trajectory from streaming video without using future frames. |
|
Liting Wen, Zimo Yang, Xianlin Zhang, Chi Ding, Mingdao Wang, Xueming Li
ACM Multimedia Asia, 2025 (Oral Presentation)
arXiv /
An approach enables high-fidelity 3D face reconstruction from just one hand-drawn sketch, achieving accurate geometry and expressive details. |
|
Yiwen Zhao, Yang Wang, Liting Wen, Hengyuan Zhang, Xingqun Qi
ICCV, 2025
project page / paper / code
A unified framework that generates group dances of free-number dancers, harmonically aligned with music while ensuring motion diversity and cross-dancer coordination. |
|
Louise Liuyue Xie, Avik Kuthiala, George Zhihong Wei, Ce Zheng, Ananya Bal, Mosam Dabhi, Liting Wen, Taru Rustagi, Ethan Lai, Sushil Khyalia, Rohan Choudhury, Morteza Ziyadi, Xu Zhang, Hao Yang, László A. Jeni
AAAI, 2026
project page / paper
A benchmark that evaluates multimodal large language models on real-world audio-visual understanding, highlighting the gap between current models and human comprehension in integrating sound, vision, and context. |
|
Wei Wu, Haipeng Peng, Liting Wen, Yuhong Liu, Fenghua Tong, Lixiang Li
IEEE Sensors Journal, 2023
paper /
A secure, efficient data transmission method with multilevel privacy protection based on chaotic compressive sensing, tailored for resource-limited IoT sensors. |
|
|
|
Advisor: Prof. Ying-Qing Xu and Prof. Yunbing Chen
Finalist @ Electronic Theater, Chinagraph, 2022
exhibited @ Asia Digital Art Exhibition, 2022exhibited @ Apsara Conference, 2022 Processed EEG signals and developed diverse artistic visualizations; this work was covered by major media and shared by 200+ media platforms in China, reaching an audience of over 500 million. |
|
|
|
▪ I'm a game developer 🕹️ & 3D art enthusiast 🎨. I love building immersive 3D worlds — it's my way of expressing what words cannot. These wonderful moments continually energize and inspire my research in 3D vision 💗 !! [My Gallery] ✨ Here are some of my works in AR/VR, VFX (visual effects), 3D modeling, and games: |
|
|
|
Liting Wen, Liwei Wang, Yingqi Tian, Zimo Yang, Zhenkun Zheng Grand Award, 3D Digital Innovation Design Competition, Beijing, 2023[Tools: Unity, RealityCapture] We conducted on-site 3D scanning and refinement of Lord Rabbit; developed multiple interactive features including card-based model switching, gesture-controlled rotation and scaling, and 3D model coloring. |
|
|
|
|
▪ Checkpoints 🚩: ------------------ ◦ Outstanding Graduate of Beijing (top 5%, highest graduation honors) 2024 ◦ National Innovation Award, Undergraduate Innovation and Entrepreneurship Program (China) 2023 ◦ Finalist at Electronic Theater, Chinagraph 2022 ◦ Second Prize, Chinese Mathematics Competitions 2021 ◦ Second Prize, National Mathematics Olympiad (Sichuan Division, China) 2019 ------------------ ◦ BUPT Undergrad Scholarship (for academic excellence, honored all eligible years) 2021 / 2022 / 2023 ◦ BUPT Distinguished Contributor in Culture & Sports 2022 / 2023 |
|
|
Template stolen from Jon Barron. |
