Haiping Wang

Wuhan University Ph.D. Wuhan University (2023-Now)

I am currently a second-year Ph.D. student at LIESMARS, Wuhan University, under the supervision of Prof. Zhen Dong and Prof. Bisheng Yang. I also maintain a close collaboration with Assistant Prof. Yuan Liu from HKUST. Additionally, I am an active member of AnySync3D and maintain an open-source platform WHU-USI3DV for point cloud processing benchmarks and algorithms. My research focuses on advanced 3D vision algorithms, encompassing:

Google Scholar GitHub
News
  • 2025/01: CityAnchor, 3D-LLM for city-scale grounding, is accepted by ICLR2025.
  • 2024/12: Open-source GAGS that enables accurate open-vocabulary segmentation in a Gaussian scene.
  • 2024/10: Open-source VistaDream for Fast Image-to-3D Scene on 4090(24G).
  • 2024/04: CC4D has been accepted by TGRS.
  • 2024/01: FreeReg has been accepted by ICLR2024.
  • 2023/02: SGHR has been accepted by CVPR2023.
  • 2023/02: RoReg has been accepted by TPAMI.
Honors & Awards
  • Fundamental Project for PhD student from NSFC (国自然博士基金) 2024
  • National Scholarship for Ph.D. (Top 3%, Rank 1st in LISMARS) 2023
  • Gold Medal of Smart City Technology Innovation Award (Rank 1st) 2023
  • Outstanding Student Scholarship (Top 1%) 2020
  • Outstanding Graduate of Wuhan University (Top 5%) 2020
  • Dao-Yu Liu Innovation & Learning Scholarship - First Class (Top 5%) 2019
  • The Best Paper Award at the National Lidar Conference (Top 10) 2018
  • National Scholarship for Postgraduates (Top 3%) 2017 & 2018
Selected Publications (view all )
CityAnchor':' City-scale 3D Visual Grounding with Multi-modality LLMs
CityAnchor':' City-scale 3D Visual Grounding with Multi-modality LLMs

Jinpeng Li, Haiping Wang*, Jiabin Chen, Yuan Liu†, Zhiyang Dou, Yuexin Ma, Sibei Yang, Yuan Li, Wenping Wang, Zhen Dong, Bisheng Yang†

3D-LLM

ICLR 2025

We present a two-stage (coarse-to-fine) 3D visual grounding system by tuning Large Vision Language Model to accurately find targets in city-scale point clouds from text descriptions.

[Paper] [Code]

CityAnchor':' City-scale 3D Visual Grounding with Multi-modality LLMs
CityAnchor':' City-scale 3D Visual Grounding with Multi-modality LLMs

Jinpeng Li, Haiping Wang*, Jiabin Chen, Yuan Liu†, Zhiyang Dou, Yuexin Ma, Sibei Yang, Yuan Li, Wenping Wang, Zhen Dong, Bisheng Yang†

ICLR 2025 3D-LLM

We present a two-stage (coarse-to-fine) 3D visual grounding system by tuning Large Vision Language Model to accurately find targets in city-scale point clouds from text descriptions.

[Paper] [Code]

VistaDream':' Sampling multiview consistent images for single-view scene reconstruction

Haiping Wang, Yuan Liu†, Ziwei Liu, Zhen Dong†, Wenping Wang, Bisheng Yang

Text/Image-to-3D Scene Generation

arXiv 2024

VistaDream is a training-free framework to reconstruct a high-quality 3D scene from a single-view image. The key idea is to sample multi-view consistent high-quality images from pre-trained single-view diffusion models.

[Paper] [Code] [Project Page]

VistaDream':' Sampling multiview consistent images for single-view scene reconstruction
VistaDream':' Sampling multiview consistent images for single-view scene reconstruction

Haiping Wang, Yuan Liu†, Ziwei Liu, Zhen Dong†, Wenping Wang, Bisheng Yang

arXiv 2024 Text/Image-to-3D Scene Generation

VistaDream is a training-free framework to reconstruct a high-quality 3D scene from a single-view image. The key idea is to sample multi-view consistent high-quality images from pre-trained single-view diffusion models.

[Paper] [Code] [Project Page]

GAGS':' Granularity-Aware 3D Feature Distillation for Gaussian Splatting

Yuning Pang*, Haiping Wang*, Yuan Liu†, Chenglu Wen, Zhen Dong†, Bisheng Yang

3D Open-vocabulary Understanding

arXiv 2024

GAGS learns a 3D Gaussian field associated with semantic features, which enables accurate open-vocabulary 3D visual grounding in the scene.

[Paper] [Code] [Project Page]

GAGS':' Granularity-Aware 3D Feature Distillation for Gaussian Splatting
GAGS':' Granularity-Aware 3D Feature Distillation for Gaussian Splatting

Yuning Pang*, Haiping Wang*, Yuan Liu†, Chenglu Wen, Zhen Dong†, Bisheng Yang

arXiv 2024 3D Open-vocabulary Understanding

GAGS learns a 3D Gaussian field associated with semantic features, which enables accurate open-vocabulary 3D visual grounding in the scene.

[Paper] [Code] [Project Page]

FreeReg':' Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
FreeReg':' Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators

Haiping Wang*, Yuan Liu*, Bing Wang, Yujing Sun, Zhen Dong†, Wenping Wang, Bisheng Yang†

Image-to-Point Cloud Registration

International Conference on Learning Representations (ICLR) 2024

FreeReg extracts cross-modality features from pretrained diffusion models and monocular depth estimators for accurate zero-shot image-to-point cloud registration.

[Paper] [Code] [Project Page] [Video]

FreeReg':' Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
FreeReg':' Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators

Haiping Wang*, Yuan Liu*, Bing Wang, Yujing Sun, Zhen Dong†, Wenping Wang, Bisheng Yang†

International Conference on Learning Representations (ICLR) 2024 Image-to-Point Cloud Registration

FreeReg extracts cross-modality features from pretrained diffusion models and monocular depth estimators for accurate zero-shot image-to-point cloud registration.

[Paper] [Code] [Project Page] [Video]

A novel method for registration of MLS and stereo reconstructed point clouds
A novel method for registration of MLS and stereo reconstructed point clouds

Xiaochen Yang*, Haiping Wang*, Zhen Dong†, Yuan Liu, Yuhan Li, Bisheng Yang†

Point Cloud Pariwise Registration

IEEE Transactions on Geoscience and Remote Sensing (T-GRS, IF:8.2) 2024

A fast and robust SO(2)-equivariant point cloud descriptor designed for aligning point clouds confirming 4DoF rigid-transformation such as MLS and TLS data.

[Paper] [Code]

A novel method for registration of MLS and stereo reconstructed point clouds
A novel method for registration of MLS and stereo reconstructed point clouds

Xiaochen Yang*, Haiping Wang*, Zhen Dong†, Yuan Liu, Yuhan Li, Bisheng Yang†

IEEE Transactions on Geoscience and Remote Sensing (T-GRS, IF:8.2) 2024 Point Cloud Pariwise Registration

A fast and robust SO(2)-equivariant point cloud descriptor designed for aligning point clouds confirming 4DoF rigid-transformation such as MLS and TLS data.

[Paper] [Code]

Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting
Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting

Haiping Wang*, Yuan Liu*, Zhen Dong†, Yulan Guo, Yu-Shen Liu, Wenping Wang, Bisheng Yang†

Point Cloud Multiview Registration

The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2023

A simple and effective multiview point cloud registration method containing a sparse pose graph construction and a robust IRLS method, achieving SoTA registration performances on the 3D(Lo)Match, ScanNet, and ETH datasets (2023).

[Paper] [Code] [Video]

Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting
Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting

Haiping Wang*, Yuan Liu*, Zhen Dong†, Yulan Guo, Yu-Shen Liu, Wenping Wang, Bisheng Yang†

The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2023 Point Cloud Multiview Registration

A simple and effective multiview point cloud registration method containing a sparse pose graph construction and a robust IRLS method, achieving SoTA registration performances on the 3D(Lo)Match, ScanNet, and ETH datasets (2023).

[Paper] [Code] [Video]

RoReg':' Pairwise Point Cloud Registration with Oriented Descriptors and Local Rotations
RoReg':' Pairwise Point Cloud Registration with Oriented Descriptors and Local Rotations

Haiping Wang*, Yuan Liu*, Qingyong Hu, Bing Wang, Jianguo Chen, Zhen Dong†, Yulan Guo, Wenping Wang, Bisheng Yang†

Point Cloud Pariwise Registration

IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI, IF:24.3) 2023

Group-based rotation-equivariance can benefit each components of point cloud registration, including feature extraction, feature detection, feature matching, and transformation estimation. RoReg achieves SoTA registration performances on the 3D(Lo)Match and ETH datasets (2023).

[Paper] [Code] [Project Page]

RoReg':' Pairwise Point Cloud Registration with Oriented Descriptors and Local Rotations
RoReg':' Pairwise Point Cloud Registration with Oriented Descriptors and Local Rotations

Haiping Wang*, Yuan Liu*, Qingyong Hu, Bing Wang, Jianguo Chen, Zhen Dong†, Yulan Guo, Wenping Wang, Bisheng Yang†

IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI, IF:24.3) 2023 Point Cloud Pariwise Registration

Group-based rotation-equivariance can benefit each components of point cloud registration, including feature extraction, feature detection, feature matching, and transformation estimation. RoReg achieves SoTA registration performances on the 3D(Lo)Match and ETH datasets (2023).

[Paper] [Code] [Project Page]

You Only Hypothesize Once':' Point Cloud Registration with Rotation-equivariant Descriptors
You Only Hypothesize Once':' Point Cloud Registration with Rotation-equivariant Descriptors

Haiping Wang*, Yuan Liu*, Zhen Dong†, Wenping Wang

Point Cloud Pariwise Registration

ACM Multimedia (MM) 2022

Endow local descriptors of point clouds with rotation equivariance based on the icosahedral group learning, achieving SoTA registration performances on the 3D(Lo)Match, ETH, and WHU-TLS datasets (2022).

[Paper] [Code] [Project Page] [Video]

You Only Hypothesize Once':' Point Cloud Registration with Rotation-equivariant Descriptors
You Only Hypothesize Once':' Point Cloud Registration with Rotation-equivariant Descriptors

Haiping Wang*, Yuan Liu*, Zhen Dong†, Wenping Wang

ACM Multimedia (MM) 2022 Point Cloud Pariwise Registration

Endow local descriptors of point clouds with rotation equivariance based on the icosahedral group learning, achieving SoTA registration performances on the 3D(Lo)Match, ETH, and WHU-TLS datasets (2022).

[Paper] [Code] [Project Page] [Video]

All publications