Jiepeng Wang

Ph.D., HKU & TeleAI

jiepeng@connect.hku.hk

I'm a research scientist specializing in generative AI at Institute of Artificial Intelligence (TeleAI), China Telecom. I received my Ph.D. at The University of Hong Kong (HKU), advised by Prof. Wenping Wang and Prof. Taku Komura. Before that, I got my master's degree at Shanghai Jiao Tong University, advised by Prof. Genliang Chen and Prof. Hao Wang, and got my bachelor's degree at Shandong University.

I have broad interests in video generation, world model, 3D reconstruction/generation, and robotics, with a focus on applying generative AI techniques to address cutting-edge challenges in these areas. I'm also a member of AnySyn3D , a non-profit research interest group focusing on various fundamental topics in 3D.

I'm looking for highly motivated research interns. We currently have multiple positions available, focusing on, but not limited to, video generation/editing, 2D foundation models, and 3D reconstruction/generation. If you are interested in these areas or would like to discuss any of these research topics, feel free to send me an email (please include your CV if applying for an internship).

[Github] [Google Scholar]

Experience

2022.06-2023.12 Microsoft Research Asia, Research intern, 3D understanding/generation

2024.03-2024.08 ShanghaiTech Univeristy, Visiting researcher, 3D reconstruction

2024.09-2024.11 AIsphere, Research intern, Image/video generation

Publications

	MMGen: Unified Multi-modal Image Generation and Understanding in One Go Jiepeng Wang* , Zhaoqing Wang, Hao Pan, Yuan Liu, Dongdong Yu, Changhu Wang^†, Wenping Wang arXiv 2025* (* Equal contribution , † Corresponding author) [Paper] [Code] [Project Page]
	AGS-Mesh: Adaptive Gaussian Splatting and Meshing with Geometric Priors for Indoor Room Reconstruction Using Smartphones Xuqian Ren ‡, Matias Turkulainen, Jiepeng Wang †, Otto Seiskari, Iaroslav Melekhov, Juho Kannala, Esa Rahtu 3DV 2025 (‡ Project lead , † Corresponding author) [Paper] [Code] [Project Page]
	StructRe: Rewriting for Structured Shape Modeling Jiepeng Wang, Hao Pan, Yang Liu, Xin Tong, Taku Komura, Wenping Wang Transactions on Graphics (Provisionally accepted, will be presented at SIGGRAPH2025) [Paper] [Code] [Project Page]
	PanoSLAM: Panoptic 3D Scene Reconstruction via Gaussian SLAM Runnan Chen, Zhaoqing Wang, Jiepeng Wang, Yuexin Ma, Mingming Gong, Wenping Wang, Tongliang Liu arXiv 2024 [Paper] [Code]
	GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction Jiepeng Wang, Yuan Liu, Peng Wang, Cheng Lin, Junhui Hou, Xin Li, Taku Komura, Wenping Wang ArXiv 2024 [Paper] [Code] [Project Page]
	SuperGaussians: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors Rui Xu, Wenyue Chen, Jiepeng Wang, Yuan Liu, Peng Wang, Lin Gao, Shiqing Xin, Taku Komura, Xin Li, Wenping Wang ArXiv 2024 [Paper] [Code] [Project Page]
	MoDGS: Dynamic Gaussian Splatting from Causually-captured Monocular Videos Qingming Liu, Yuan Liu, Jiepeng Wang, Xianqiang Lv, Peng Wang, Wenping Wang, Junhui Hou ICLR 2025 [Paper] [Code] [Project Page]
	ComboStoc: Combinatorial Stochasticity for Diffusion Generative Model Rui Xu, Jiepeng Wang, Hao Pan, Yang Liu, Xin Tong, Shiqing Xin, Changhe Tu, Taku Komura, Wenping Wang ArXiv 2024 [Paper] [Code] [Project Page]
	A Compliant Gripper System for Delicate Object Grasping through Intrinsic Contact Sensing Tao Yu, Jiepeng Wang, Shujie Tang, Xingyue Zhu, Genliang Chen RSS 2024 Workshop [Paper]
	Batch-based Model Registration for Fast 3D Sherd Reconstruction Jiepeng Wang, Congyi Zhang, Peng Wang, Xin Li, Peter J. Cobb, Christian Theobalt, Wenping Wang ICCV 2023 [Paper] [Code] [Project Page]
	NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images Yuan Liu, Peng Wang, Cheng Lin, Xiaoxiao Long, Jiepeng Wang, Lingjie Liu, Taku Komura, Wenping Wang SIGGRAPH 2023 [Paper] [Code] [Project Page]
	NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors Jiepeng Wang, Peng Wang, Xiaoxiao Long, Christian Theobalt, Taku Komura, Lingjie Liu, Wenping Wang ECCV 2022 [Paper] [Code] [Project Page]
	A New Type of Planar Two Degree-of-Freedom Remote Center-of-Motion Mechanism Inspired by the Peaucellier–Lipkin Straight-Line Linkage Genliang Chen, Jiepeng Wang, Hao Wang Journal of Mechanical Design, 2018 [Paper]
	Design and kinematic analysis of a spherical parallel manipulator using concurrent planar parallelogram linkages Genliang Chen, Weidong Yu, Jiepeng Wang, Hao Wang Journal of Mechanical Engineering Science, 2018 [Paper]