Yutian Chen | 陈羽田 Ph.D. StudentThe Chinese University of Hong Kong |
I am a second-year Ph.D. student at MMLab, The Chinese University of Hong Kong, supervised by Prof. Tianfan Xue. Before that, I received my Bachelor's degree in Robotics Engineering from Chu Kochen Honors College, Zhejiang University, advised by Prof. Yue Wang. I also spent a wonderful time at Shanghai AI Laboratory as a research intern, mentored by Dr. Shi Guo.
|
AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model
Yutian Chen, Shi Guo, Renbiao Jin, Tianshuo Yang, Xin Cai, Yawen Luo, Mingxin Yang, Mulin Yu, Linning Xu, Tianfan Xue SIGGRAPH Asia, 2026 Project page / Paper / Code / Video AnyRecon enables high-quality and large-scale 3D reconstruction from sparse inputs. |
|
RealVDeblur: One-Step Diffusion for Generalizable Real-World Video Deblurring
Renbiao Jin*, Mingxin Yang*, Yutian Chen, Junhao Zhuang, Xin Cai, Mulin Yu, Linning Xu, Wenxian Yu, Danping Zou†, Shi Guo†, Tianfan Xue arXiv, 2026 Project page / Paper / Code A one-step video diffusion model for generalizable real-world video deblurring and improved downstream 3D perception. |
|
HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
Tianshuo Yang, Guanyu Chen, Yutian Chen, Zhixuan Liang, Yitian Liu, Zanxin Chen, Chunpu Xu Haotian Liang, Jiangmiao Pang, Yao Mu, Ping Luo, arXiv, 2026 Project page / Paper / Code A visual-grounded-centric hierarchical framework that explicitly decouples high-level semantic planning from low-level motor control |
|
ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling
Yawen Luo, Xiaoyu Shi, Junhao Zhuang, Yutian Chen, Quande Liu, Xintao Wang, Pengfei Wan, Tianfan Xue European Conference on Computer Vision (ECCV), 2026 Project page / Paper / Code A novel causal multi-shot architecture that enables interactive storytelling and efficient on-the-fly frame generation, achieving 16 FPS on a single NVIDIA GPU. |
|
AsyncEvGS: Asynchronous Event-Assisted Gaussian Splatting for Handheld Motion-Blurred Scenes
Jun Dai*, Renbiao Jin*, Bo Xu, Yutian Chen, Linning Xu, Mulin Yu, Tianfan Xue†, Shi Guo† arXiv, 2026 Project page / Paper An asynchronous high-resolution RGB–Event system for robust 3DGS reconstruction from severely motion-blurred handheld captures. |
|
4D E-SloMo: 4D Reconstruction for High Speed Scene using a Hybrid RGB-Event Multi-View System
Bo Xu, Jun Dai, Yutian Chen, Linning Xu, Mulin Yu, Yujin Wang, Shi Guo, Xinyi Le, Tianfan Xue Computer Vision and Pattern Recognition Findings (CVPR), 2026 A hybrid RGB-Event multi-view system for high-quality 4D reconstruction of high-speed, room-scale dynamic scenes. |
|
4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture
Yutian Chen, Shi Guo, Tianshuo Yang, Lihe Ding, Xiuyuan Yu, Jinwei Gu, Tianfan Xue ACM SIGGRAPH Asia, 2025 Project page / Paper / Code Our method can reconstruct high speed and complex 4D motion with high quality. |
|
Event-assisted 12-stop HDR Imaging of Dynamic Scene
Shi Guo†, Zixuan Chen, Ziran Zhang, Yutian Chen, Gangwei Xu, Tianfan Xue arXiv, 2024 Project page / Paper / Code (Coming soon) Using event camera, our method present the first attempt at 12-stop HDR imaging for dynamic scenes. |
|
Event-Based Motion Magnification
Yutian Chen, Shi Guo†, Fangzheng Yu, Feng Zhang, Jinwei Gu, Tianfan Xue European Conference on Computer Vision (ECCV), 2024 project page / video / paper / code Detecting and magnifying imperceptible high-frequency motions in real-world scenarios with our RGB-event dual camera system. |
|
TimeLens-XL: Real-time Event-based Video Frame Interpolation with Large Motion
Yongrui Ma, Shi Guo, Yutian Chen, Tianfan Xue, Jinwei Gu European Conference on Computer Vision (ECCV), 2024 project page / video / paper / code A real-time video frame interpolation method for large motion with a hybrid neuromorphic camera. |
Hong Kong PhD Fellowship Scheme (HKPFS), 2024
Top Ten Honors Students in Chu Kochen Honors College, 2023
National Scholarship, 2022
National Scholarship, 2021