GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure
, Junhwa Hur, Charles Herrmann, Fangneng Zhan, Todd Zickler, ,
ECCV, 2026
About
I'm a Ph.D. student in Computer Science at , advised by . Previously, I worked closely with at Google DeepMind. I received my M.S. from , advised by and , and B.S. from the at , advised by .
Research Topics
I am broadly interested in 3D vision and geometric deep learning. My current research focuses on physics-aware visual generation.
Previously, I worked on shape analysis and generative modeling in EM imaging ( [ 
]) and CT imaging (Rib Analysis).
Additionally, I design and build robots for competition events and medical usage.
[Check the robots I built. ]
News
[06/2026] GeCo is accepted by ECCV.
[02/2026] One paper on active reconstruction is accepted by CVPR.
[12/2025] Invited talk at [3D Worlds] team, Google DeepMind.
[07/2025] One paper on 3D Curvilinear Structure Segmentation is accecpted by IEEE TMI.
[05/2025] RibFrac Challenge is accecpted by IEEE TMI.
[09/2023] RibSeg v2 is accecpted by IEEE TMI.
[06/2023] One paper on neuron growth simulation is accecpted by CMAME.
Publications
* indicates equal contribution.
GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure
, Junhwa Hur, Charles Herrmann, Fangneng Zhan, Todd Zickler, ,
ECCV, 2026
AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidance
Tianling Xu, Shengzhe Gan, , Yuelei Li, Fangneng Zhan, , Paul Liang
CVPR, 2026
Frenet-Serret Frame-based Decomposition for Part Segmentation of 3D Curvilinear Structures
, , , , , Wenjie Yin, , , ,
IEEE Transactions on Medical Imaging (IEEE TMI), 2025
RibFrac Challenge: Rib Fracture Detection, Segmentation and Classification from CT Scans
*, Rui Shi*, Liang Jin, Xiaoyang Huang, , , , Youjun E, Jiaqi Zhang, Jianying Liu, Pengfei Liu, Zhizhong Chai, Yongjie Xiao, Hao Chen, Liming Xu, Bang Du, Xiangyi Yan, Hao Tang, Adam Alessio, Gregory Holste, Jiapeng Zhang, Xiaoming Wang, Jianye He, Lixuan Che, , ,
IEEE Transactions on Medical Imaging (IEEE TMI), 2025
RibSeg v2: A Large-scale Benchmark for Rib Labeling and Anatomical Centerline Extraction
Liang Jin*, *, , , , , , , ,
IEEE Transactions on Medical Imaging (IEEE TMI), 2023
Biomimetic IGA neuron growth model with neurite morphometric features and CNN-based prediction
, , , ,
Computer Methods in Applied Mechanics and Engineering (CMAME), 2023
RibSeg Dataset and Strong Point Cloud Baselines for Rib Segmentation from CT Scans
*, *, , ,
International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2021
Robotics
,
[2021 - 2022] Patient Care Technologies for Permanent Ambulatory Artificial Lung SupportAdvisor: &
Develop technologies that enable permanent, at-home artificial lung support to allow chronic lung disease patients to lead longer, more normal lives.
,
[2018 - 2020] SJTU-VEX Robotics Project [Check the events here.]Advisor:
I'm one of the founding members of the SJTU VEX Lab, and I have been designing, building, and programming robots for over two years, competing for VEX U robotics world tournaments.
Awards
College of Engineering,
[2021] Outstanding Graduate of Shanghai Jiao Tong University
[2019]
,
[2018] Create Award, Robot Skills Finalist, and Silver Award
2018 12th Asia-Pacific Robotics Championship, Asian Robotics League
[2018]
[2018] Leading Student Ambassador, Excellent Student Presentation Award
,
[2016] First Prize and Best Con in Shanghai ( Shanghai)
Shanghai Physical Society, China
Misc.
Teaching
: COMPSCI 1090A: Data Science 1: Introduction to Data Science, Fall'25: COMPSCI 1090A: Data Science 1: Introduction to Data Science, Fall'24
: COM SCI 960.01: Artificial Intelligence and Data Science, Aug'21; ENGL 902:Research Methodologies, Aug'21; ENGL 901: Academic Writing, Aug'21.