About Me

I am currently a first-year Ph.D. student in ISD at The Hong Kong University of Science and Technology, where I am a member of the Intelligent Graphics Lab (IGL-HKUST), supervised by Prof. Yuan Liu.

Prior to this, I obtained my master's degree from Tsinghua University in 2025, advised by Prof. Haoqian Wang, and my bachelor's degree in Software Engineering from Northwestern Polytechnical University in 2022. I have also been fortunate to work closely with Yikang Ding and Xiaoyu Shi.

My research interests lie in video generation, 3D computer vision, vision-language models (VLMs), and embodied AI, with a focus on enabling intelligent agents to perceive, understand, and interact with the 3D world.

I welcome opportunities to collaborate on related research. Please feel free to email me at yingsh.zou@gmail.com.

Research interests

Video Generation 3D Computer Vision Vision-Language Models Embodied AI

Selected Publications

^* Equal contribution. ^† Corresponding author.

Mise-en-Video multi-shot generation result

SIGGRAPH Asia 2026

Mise-en-Video: Fine-Grained 3D Control for Multi-Shot Video Generation

Yingshuang Zou, Xiaoyu Shi^†, Yawen Luo, Ziang Li, Qinghe Wang, Mengfei Li, Chengfeng Zhao, Xintao Wang, Pengfei Wan, Kun Gai, Yuan Liu^†

ACM SIGGRAPH Asia Conference Papers, 2026

Fine-grained 3D control for coherent multi-shot video generation through hierarchical narrative conditioning and 3D-aware layout guidance.

Project Paper

BMVC 2025

MuDG: Taming Multi-modal Diffusion with Gaussian Splatting for Urban Scene Reconstruction

Yingshuang Zou^*, Yikang Ding^*, Chuanrui Zhang, Jiazhe Guo, Bohan Li, Xiaoyang Lyu, Feiyang Tan, Xiaojuan Qi, Haoqian Wang^†

British Machine Vision Conference (BMVC), 2025

A controllable multi-modal diffusion framework with Gaussian Splatting for photorealistic urban scene reconstruction and synthesis.

Project Paper Code

UniScene controllable driving scene generation results

CVPR 2025

UniScene: Unified Occupancy-centric Driving Scene Generation

Bohan Li^*, Jiazhe Guo^*, Hongsi Liu^*, Yingshuang Zou^*, Yikang Ding^*, Xiwu Chen, Hu Zhu, Feiyang Tan, Chi Zhang, Tiancai Wang, Shuchang Zhou, Li Zhang, Xiaojuan Qi, Hao Zhao, Mu Yang, Wenjun Zeng, Xin Jin^†

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

A unified occupancy-centric framework for controllable generation of semantic occupancy, multi-view video, and LiDAR in driving scenes.

Project Paper Code

AAAI 2025

TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers

Chuanrui Zhang^*, Yingshuang Zou^*, Zhuoling Li, Minmin Yi, Haoqian Wang^†

AAAI Conference on Artificial Intelligence (AAAI), 2025

A transformer-based approach for generalizable 3D Gaussian Splatting from sparse views with depth-aware feature matching.

Project Paper Code

M²Depth method and depth estimation results

ECCV 2024 Oral

M²Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation

Yingshuang Zou^*, Yikang Ding^*, Xi Qiu, Minglei Lu, Haoqian Wang^†, Haotian Zhang^†

European Conference on Computer Vision (ECCV), 2024 — Oral

Self-supervised metric depth estimation that fuses spatial-temporal information from two-frame surround-view images with strong semantic priors.

Project Paper

Projects

Dynamic driving scene reconstructed with Gaussian Splatting

Research Project

Gaussian Splatting for Dynamic Driving Scenes

Developed a Gaussian Splatting representation for real-time reconstruction and novel-view synthesis of dynamic driving scenes from six surround-view cameras, jointly optimizing appearance, depth, semantics, and optical flow.

Competitions

ICRA 2020

DJI RoboMaster AI Challenge

Third Prize · 6th of 72 teams

Developed a Gazebo-based platform for sensor simulation and autonomous navigation, with perception and motion-planning algorithms deployed on physical robots.

Emulator Perception Strategy Planning