Sheng Yang 🥤
Sheng Yang

Principal Researcher

NIO

Nice to Meet You !~

I am currently the Founding Director and Principal Researcher of NIO AI Research, working closely with Prof. Shaoqing Ren on cutting-edge architectures and algorithms for autonomous driving.

Before joining NIO, I worked as a Director of the Alibaba Autonomous Driving Lab, where I led the overall algorithmic architecture across perception, generative reconstruction and SLAM. I successfully launched the Robovan project sponsored by CaiNiao CTO Qiang Li, and deployed our architectural solution across all L4 unmanned vehicles, enabling millions of successful customer deliveries.

I received my Ph.D. in Computer Science from the Graphics and Geometric Computing Group, Tsinghua University, advised by Prof. Shi-Min Hu. I earned my B.Eng. in Computer Science from Wuhan University, ranking first in our grade.

🍀 I enjoy working with full-time researchers and highly motivated research interns. We are actively recruiting —— feel free to reach out via Intern, Campus and Social Links.

Interests
  • World Foundation Model
  • Spatial Representation Learning
  • Generation / Perception / Action
Education

  • Ph.D. in Computer Science, 2019

    Tsinghua University

  • B.Eng. in Computer Science, 2014

    Wuhan University

Released Projects
CaiNiao Urban Robovan
Generative Scene 3R
GT Unmanned Vehicle
Data Curation Chain
Publications
LiDAR-GS++: Improving LiDAR Gaussian Reconstruction via Diffusion Priors
LiDAR-GS++: Improving LiDAR Gaussian Reconstruction via Diffusion Priors
2026. AAAI.
Qifeng Chen, Jiarun Liu, Rengan Xie, Tao Tang, Sicong Du, Yiru Zhao, Yuchi Huo, Sheng Yang†
PDF Cite Code
GUIDE: Gaussian Unified Instance Detection for Enhanced Obstacle Perception in Autonomous Driving
GUIDE: Gaussian Unified Instance Detection for Enhanced Obstacle Perception in Autonomous Driving
2026. AAAI.
Chunyong Hu*, Qi Luo*, Jianyun Xu, Song Wang, Qiang Li, Sheng Yang†
PDF Cite Code
GS-RoadPatching: Inpainting Gaussians via 3D Searching and Placing for Driving Scenes
GS-RoadPatching: Inpainting Gaussians via 3D Searching and Placing for Driving Scenes
2025. SIGGRAPH Asia.
Guo Chen*, Jiarun Liu*, Sicong Du, Chenming Wu, Deqi Li, Shi-Sheng Huang†, Guofeng Zhang, Sheng Yang†
PDF Cite Code
RTMap: Real-Time Recursive Mapping with Change Detection and Localization
RTMap: Real-Time Recursive Mapping with Change Detection and Localization
2025. ICCV.
Yuheng Du*, Sheng Yang*†, Lingxuan Wang, Zhenghua Hou, Chengying Cai, Zhitao Tan, Mingxia Chen, Shi-Sheng Huang, Qiang Li
PDF Cite Code
RGE-GS: Reward-Guided Expansive Driving Scene Reconstruction via Diffusion Priors
RGE-GS: Reward-Guided Expansive Driving Scene Reconstruction via Diffusion Priors
2025. ICCV.
Sicong Du*, Jiarun Liu*, Qifeng Chen, Hao-Xiang Chen, Tai-Jiang Mu, Sheng Yang†
PDF Cite Code
SAM4D: Segment Anything in Camera and LiDAR Streams
SAM4D: Segment Anything in Camera and LiDAR Streams
2025. ICCV.
Jianyun Xu*, Song Wang*, Ziqian Ni*, Chunyong Hu, Sheng Yang†, Jianke Zhu, Qiang Li
PDF Cite Code
Language Driven Occupancy Prediction
Language Driven Occupancy Prediction
2025. ICCV.
Zhu Yu*, Bowen Pang*, Lizhe Liu, Runmin Zhang, Qiang Li, Si-Yuan Cao, Maochun Luo, Mingxia Chen, Sheng Yang, Hui-Liang Shen
PDF Cite Code
Industrial-Grade Sensor Simulation via Gaussian Splatting: A Modular Framework for Scalable Editing and Full-Stack Validation
Industrial-Grade Sensor Simulation via Gaussian Splatting: A Modular Framework for Scalable Editing and Full-Stack Validation
2025. IROS.
Xianming Zeng*, Sicong Du*, Qifeng Chen*, Lizhe Liu, Haoyu Shu, Jiaxuan Gao, Jiarun Liu, Jiulong Xu, Jianyun Xu, Mingxia Chen, Yiru Zhao, Peng Chen, Yapeng Xue, Chunming Zhao, Sheng Yang†, Qiang Li
PDF Cite
Para-Lane: Multi-Lane Dataset Registering Parallel Scans for Benchmarking Novel View Synthesis
Para-Lane: Multi-Lane Dataset Registering Parallel Scans for Benchmarking Novel View Synthesis
2025. International Conference on 3D Vision.
Ziqian Ni, Sicong Du, Zhenghua Hou, Chenming Wu, Sheng Yang†
PDF Cite Dataset
A Survey of Recent Advances in Generative 3D Reconstruction
A Survey of Recent Advances in Generative 3D Reconstruction
2025. Journal of Computer Science and Technology.
Shi-Sheng Huang, Shao-Kui Zhang, Sheng Yang, Jian-Wei Guo, Hua Huang
PDF Cite
LiDAR-GS: Real-time LiDAR Re-Simulation using Gaussian Splatting
LiDAR-GS: Real-time LiDAR Re-Simulation using Gaussian Splatting
2024. ArXiv Preprint.
Qifeng Chen, Sheng Yang†, Sicong Du, Tao Tang, Peng Chen, Yuchi Huo
PDF Cite Code
WING: Wheel-Inertial Neural Odometry with Ground Manifold Constraints
WING: Wheel-Inertial Neural Odometry with Ground Manifold Constraints
2024. IEEE Transactions on Intelligent Vehicles.
Chenxing Jiang, Kunyi Zhang, Sheng Yang, Shaojie Shen, Chao Xu, Fei Gao
PDF Cite
360-VIO: A Robust Visual-Inertial Odometry Using a 360° Camera
360-VIO: A Robust Visual-Inertial Odometry Using a 360° Camera
2023. IEEE Transactions on Industrial Electronics.
Qi Wu, Xiangyu Xu, Xieyuanli Chen, Ling Pei, Chao Long, Junyuan Deng, Guoqing Liu, Sheng Yang, Shilei Wen, Wenxian Yu
PDF Cite
SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud
SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud
2022. ECCV.
Xiangrui Zhao, Sheng Yang, Tianxin Huang, Jun Chen, Teng Ma, Mingyang Li, Yong Liu
PDF Cite Code
DIDO: Deep Inertial Quadrotor Dynamical Odometry
DIDO: Deep Inertial Quadrotor Dynamical Odometry
2022. IROS (with RAL).
Kunyi Zhang, Chenxing Jiang, Jinghang Li, Sheng Yang, Teng Ma, Chao Xu, Fei Gao
PDF Cite Code Video
The Visual-Inertial-Dynamical Multirotor Dataset
The Visual-Inertial-Dynamical Multirotor Dataset
2022. ICRA.
Kunyi Zhang*, Tiankai Yang*, Ziming Ding, Sheng Yang, Teng Ma, Mingyang Li, Chao Xu, Fei Gao
PDF Cite Code Video
Road Mapping and Localization Using Sparse Semantic Visual Features
Road Mapping and Localization Using Sparse Semantic Visual Features
2021. ICRA (with RAL).
Wentao Cheng*, Sheng Yang*, Maomin Zhou, Ziyuan Liu, Yiming Chen, Mingyang Li
PDF Cite
Noise-Resilient Reconstruction of Panoramas and 3D Scenes Using Robot-Mounted Unsynchronized Commodity RGB-D Cameras
Noise-Resilient Reconstruction of Panoramas and 3D Scenes Using Robot-Mounted Unsynchronized Commodity RGB-D Cameras
2020. ACM Transactions on Graphics.
Sheng Yang, Beichen Li, Yan-Pei Cao, Hongbo Fu, Yu-Kun Lai, Leif Kobbelt, Shi-Min Hu
PDF Cite
ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings
ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings
2020. CVPR.
Jiahui Huang, Sheng Yang, Tai-Jiang Mu, Shi-Min Hu
PDF Cite Code
Morphing and Sampling Network for Dense Point Cloud Completion
Morphing and Sampling Network for Dense Point Cloud Completion
2020. AAAI.
Minghua Liu, Lu Sheng, Sheng Yang, Jing Shao, Shi-Min Hu
PDF Cite Code Dataset
ClusterSLAM: A SLAM Backend for Simultaneous Rigid Body Clustering and Motion Estimation
ClusterSLAM: A SLAM Backend for Simultaneous Rigid Body Clustering and Motion Estimation
2019. ICCV.
Jiahui Huang, Sheng Yang, Zishuo Zhao, Yu-Kun Lai, Shi-Min Hu
PDF Cite Dataset
HeteroFusion: Dense Scene Reconstruction Integrating Multi-Sensors
HeteroFusion: Dense Scene Reconstruction Integrating Multi-Sensors
2019. IEEE Transactions on Visualization and Computer Graphics.
Sheng Yang, Beichen Li, Minghua Liu, Yu-Kun Lai, Leif Kobbelt, Shi-Min Hu
PDF Cite
Probabilistic Projective Association and Semantic Guided Relocalization for Dense Reconstruction
Probabilistic Projective Association and Semantic Guided Relocalization for Dense Reconstruction
2019. ICRA.
Sheng Yang, Zheng-Fei Kuang, Yan-Pei Cao, Yu-Kun Lai, Shi-Min Hu
PDF Cite
A Robust Pose Graph Approach for City Scale LiDAR Mapping
A Robust Pose Graph Approach for City Scale LiDAR Mapping
2018. IROS.
Sheng Yang, Xiaoling Zhu, Xing Nian, Lu Feng, Xiaozhi Qu, Teng Ma
PDF Cite
Saliency-aware Real-time Volumetric Fusion for Object Reconstruction
Saliency-aware Real-time Volumetric Fusion for Object Reconstruction
2017. Computer Graphics Forum.
Sheng Yang, Kang Chen, Minghua Liu, Hongbo Fu, Shi-Min Hu
PDF Cite
View Suggestion for Interactive Segmentation of Indoor Scenes
View Suggestion for Interactive Segmentation of Indoor Scenes
2017. Computational Visual Media.
Sheng Yang, Jie Xu, Kang Chen, Hongbo Fu
PDF Cite