Baorui Ma

I am a researcher at Beijing Academy of Artificial Intelligence (BAAI). I received my PhD degree from the School of Software, Tsinghua University, advised by Prof. Yu-Shen Liu.

My research interests lie in the area of 3D computer vision, 3D foundation models, 3D reconstruction, multi-view 3D reconstruction and surface reconstruction from point clouds.

Email | GitHub | Google Scholar | LinkedIn

Research

(*: Equal Contribution, #: corresponding author)

	You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale Baorui Ma, Huachen Gao, Haoge Deng, Zhengxiong Luo,Tiejun Huang, Lulu Tang#,Xinlong Wang# Conference on Computer Vision and Pattern Recognition (CVPR, CCF-A), 2025 (Highlight, ~3% acceptance rate*) [arxiv] \| [Project page] \| [Code] \| [Dataset] \| [Post] See3D is a scalable visual-conditional MVD model for open-world 3D creation, which can be trained on web-scale video collections without camera pose annotations.
	NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction Wenyuan Zhang , Emily Yue-ting Jia, Junsheng Zhou, Baorui Ma, Kanle Shi, Yu-Shen Liu, Zhizhong Han Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025 (Highlight, ~3% acceptance rate) project page \| arXiv We present NeRFPrior, which adopts a neural radiance field as a prior to learn signed distance fields using volume rendering for indoor scene surface reconstruction.
	Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mapping Junsheng Zhou* , Baorui Ma, Yu-Shen Liu, Zhizhong Han IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)*, 2024 project page \| IEEE Xplore \| arXiv \| code We present a fast learning framework capable of inferring signed distance functions from noisy shapes within one minute through noise-to-noise mapping.
	UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion Junsheng Zhou* , Weiqi Zhang, Baorui Ma#, Kanle Shi, Yu-Shen Liu#, Zhizhong Han arXiv, 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)*, 2024 project page \| arXiv \| code UDiFF is a 3D diffusion model for unsigned distance fields (UDFs) which is capable to generate textured 3D shapes with open surfaces from text conditions or unconditionally.
	CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimization Junsheng Zhou* , Baorui Ma, Shujuan Li, Yu-Shen Liu#, Yi Fang, Zhizhong Han IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)*, 2024 project page \| IEEE Xplore \| arXiv \| code We present CAP-UDF to represent shapes and scenes with arbitrary architecture by learning a Consistency-Aware unsigned distance function Progressively.
	3D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Clouds Junsheng Zhou* , Xin Wen, Baorui Ma, Yu-Shen Liu#, Yue Gao, Yi Fang, Zhizhong Han IEEE International Conference on Robotics and Automation (ICRA), 2024 (Oral*) project page \| arXiv \| code We present 3D-OAE, a novel self-supervised point cloud representation learning framework which is highly efficient and can be further transferred to various downstream tasks.
	GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation *Baorui Ma#*, Haoge Deng, Junsheng Zhou , Yu-Shen Liu, Tiejun Huang, Xinlong Wang# arXiv 2023. project page \| arXiv \| code We present GeoDream, a 3D generation method that incorporates explicit generalized 3D priors with 2D diffusion priors to enhance the capability of obtaining unambiguous 3D consistent geometric structures without sacrificing diversity or fidelity.
	Uni3D: Exploring Unified 3D Representation at Scale Junsheng Zhou* , Jinsheng Wang, Baorui Ma#, Yu-Shen Liu, Tiejun Huang, Xinlong Wang# International Conference on Learning Representations (ICLR, TH-CPL A), 2024 (Spotlight, ~5% acceptance rate**) Model Zoo \| arXiv \| code We present Uni3D, a unified and scalable 3D pretraining framework for large-scale 3D representation learning, and explore its limits at the scale of one billion parameters.
	Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching Junsheng Zhou* , Baorui Ma, Wenyuan Zhang, Yi Fang, Yu-Shen Liu#, Zhizhong Han Conference on Neural Information Processing Systems (NeurIPS, CCF-A), 2023 (Spotlight, ~3.6% acceptance rate*) project page \| arXiv \| code
	Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projection Junsheng Zhou* , Baorui Ma, Shujuan Li, Yu-Shen Liu#, Zhizhong Han IEEE/CVF International Conference on Computer Vision (ICCV, CCF-A)*, 2023 project page \| arXiv \| code
	Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping Baorui Ma, Yu-Shen Liu#, Zhizhong Han International Conference on Machine Learning (ICML, CCF-A), 2023 (Oral, ~2.3% acceptance rate) paper \| code

	Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignment Baorui Ma, Junsheng Zhou , Yu-Shen Liu#, Zhizhong Han Conference on Computer Vision and Pattern Recognition (CVPR, CCF-A), 2023 paper \| project page \| code
	NeAF: Learning Neural Angle Fields for Point Normal Estimation Shujuan Li, Junsheng Zhou Baorui Ma, Yu-Shen Liu#, Zhizhong Han AAAI Conference on Computing on Artificial Intelligence (AAAI, CCF-A), 2023 (Oral, ~10% acceptance rate) paper \| project page \| code

Learning Consistency-Aware Unsigned Distance Functions Progressively from Raw Point Clouds
Junsheng Zhou* , Baorui Ma* , Yu-Shen Liu#, Yi Fang, Zhizhong Han
Conference on Neural Information Processing Systems (NeurIPS, CCF-A), 2022
paper | project page | code

We present CAP-UDF to represent shapes and scenes with arbitrary architecture by learning a Consistency-Aware unsigned distance function Progressively.

Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors
Baorui Ma, Yu-Shen Liu#, Zhizhong Han
Conference on Computer Vision and Pattern Recognition (CVPR, CCF-A), 2022
paper | project page | code

Surface Reconstruction from Point Clouds by Learning Predictive Context Priors
Baorui Ma, Yu-Shen Liu#, Matthias Zwicker Zhizhong Han
Conference on Computer Vision and Pattern Recognition (CVPR, CCF-A), 2022
paper | project page | code

Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces
Baorui Ma*, Zhizhong Han* Yu-Shen Liu#, Matthias Zwicker
International Conference on Machine Learning (ICML, CCF-A), 2021 (Spotlight)

paper | code

Reconstructing 3D Shapes from Multiple Sketches using Direct Shape Optimization
Zhizhong Han, Baorui Ma, Matthias Zwicker, Yu-Shen Liu#
IEEE Transactions on Image Processing (SCI, Impact factor: 9.34) (TIP, CCF-A), 2020
paper | Demo

Honors and Awards

Outstanding Graduate of Tsinghua University, Beijing (北京市优秀毕业生), 2023.
Doctoral National Scholarship, Tsinghua University (博士国家奖学金) (2 graduates per year in School of Software), 2022.

Academic Services

Conference Reviewer: ICML, NeurIPS, CVPR, ICCV.

template adapted from this awesome website
Last updated: Oct 2023

	You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale Baorui Ma, Huachen Gao, Haoge Deng, Zhengxiong Luo,Tiejun Huang, Lulu Tang#,Xinlong Wang# Conference on Computer Vision and Pattern Recognition (CVPR, CCF-A), 2025 (Highlight, ~3% acceptance rate*) [arxiv] \| [Project page] \| [Code] \| [Dataset] \| [Post] See3D is a scalable visual-conditional MVD model for open-world 3D creation, which can be trained on web-scale video collections without camera pose annotations.
	NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction Wenyuan Zhang , Emily Yue-ting Jia, Junsheng Zhou, Baorui Ma, Kanle Shi, Yu-Shen Liu, Zhizhong Han Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025 (Highlight, ~3% acceptance rate) project page \| arXiv We present NeRFPrior, which adopts a neural radiance field as a prior to learn signed distance fields using volume rendering for indoor scene surface reconstruction.
	Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mapping Junsheng Zhou* , Baorui Ma, Yu-Shen Liu, Zhizhong Han IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)*, 2024 project page \| IEEE Xplore \| arXiv \| code We present a fast learning framework capable of inferring signed distance functions from noisy shapes within one minute through noise-to-noise mapping.
	UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion Junsheng Zhou* , Weiqi Zhang, Baorui Ma#, Kanle Shi, Yu-Shen Liu#, Zhizhong Han arXiv, 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)*, 2024 project page \| arXiv \| code UDiFF is a 3D diffusion model for unsigned distance fields (UDFs) which is capable to generate textured 3D shapes with open surfaces from text conditions or unconditionally.
	CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimization Junsheng Zhou* , Baorui Ma, Shujuan Li, Yu-Shen Liu#, Yi Fang, Zhizhong Han IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)*, 2024 project page \| IEEE Xplore \| arXiv \| code We present CAP-UDF to represent shapes and scenes with arbitrary architecture by learning a Consistency-Aware unsigned distance function Progressively.
	3D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Clouds Junsheng Zhou* , Xin Wen, Baorui Ma, Yu-Shen Liu#, Yue Gao, Yi Fang, Zhizhong Han IEEE International Conference on Robotics and Automation (ICRA), 2024 (Oral*) project page \| arXiv \| code We present 3D-OAE, a novel self-supervised point cloud representation learning framework which is highly efficient and can be further transferred to various downstream tasks.
	GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation *Baorui Ma#*, Haoge Deng, Junsheng Zhou , Yu-Shen Liu, Tiejun Huang, Xinlong Wang# arXiv 2023. project page \| arXiv \| code We present GeoDream, a 3D generation method that incorporates explicit generalized 3D priors with 2D diffusion priors to enhance the capability of obtaining unambiguous 3D consistent geometric structures without sacrificing diversity or fidelity.
	Uni3D: Exploring Unified 3D Representation at Scale Junsheng Zhou* , Jinsheng Wang, Baorui Ma#, Yu-Shen Liu, Tiejun Huang, Xinlong Wang# International Conference on Learning Representations (ICLR, TH-CPL A), 2024 (Spotlight, ~5% acceptance rate**) Model Zoo \| arXiv \| code We present Uni3D, a unified and scalable 3D pretraining framework for large-scale 3D representation learning, and explore its limits at the scale of one billion parameters.
	Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching Junsheng Zhou* , Baorui Ma, Wenyuan Zhang, Yi Fang, Yu-Shen Liu#, Zhizhong Han Conference on Neural Information Processing Systems (NeurIPS, CCF-A), 2023 (Spotlight, ~3.6% acceptance rate*) project page \| arXiv \| code
	Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projection Junsheng Zhou* , Baorui Ma, Shujuan Li, Yu-Shen Liu#, Zhizhong Han IEEE/CVF International Conference on Computer Vision (ICCV, CCF-A)*, 2023 project page \| arXiv \| code
	Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping Baorui Ma, Yu-Shen Liu#, Zhizhong Han International Conference on Machine Learning (ICML, CCF-A), 2023 (Oral, ~2.3% acceptance rate) paper \| code