Zhirui Gao

👤 Biography

Hi there👋, my name is Zhirui Gao (in Chinese: 高志锐).

I received my Ph.D. degree from National University of Defense Technology (2021–2026), supervised by Prof. Kai Xu, Prof. Wei Chen, and Assoc. Prof. Renjiao Yi. Prior to that, I earned my Bachelor's degree from China University of Geosciences (2017–2021).

I am currently a researcher at Huawei focusing on Embodied AI. My research interests broadly lie in 3D Vision and Embodied Intelligence, including 3D Reconstruction, World Models, WAM, and VLA models.

I am open to collaborations and actively recruiting research interns and full-time employees. Feel free to reach out via email!

📢 News

• [2026-07] 🆕 Our paper CGGT (Curve-Grounded Geometry Transformer) is accepted by SIGGRAPH Asia 2026 (图形学顶会).
• [2026-06] Our paper HoloTetSphere is accepted as ECCV 2026 Oral (视觉顶会).
• [2025-07] Our paper BoxFusion is accepted by Pacific Graphics 2025.
• [2025-06] 🏆 Two papers are accepted by ICCV 2025 CCF-A! (PartGS and CurveGaussian).
• [2025-02] Our paper PoseProbe is accepted by IEEE TCSVT.
• [2023-12] Our paper Fdc-nerf is accepted by ICASSP (Oral), thanks for Huachen.
• [2023-06] 🏆 Our paper 2d3d-matr is accepted by ICCV 2023 CCF-A!
• [2023-04] 🏆 Our paper Delving Into Crispness is accepted by IEEE TIP CCF-A!
• [2023-03] 🏆 Our paper NEF is accepted by CVPR 2023 CCF-A!
• [2023-01] Our paper Deep Template Matching is accepted by IEEE CVMJ (IF:18.3)!

📑 Selected Publications [Google Scholar]

🏆 SIGGRAPH Asia 2026	CGGT: Curve-Grounded Geometry Transformer for Structured Curve Reconstruction from Unposed Sparse Views Zhirui Gao, Renjiao Yi, Ruizhen Hu, Yunfan Ye, Chenyang Zhu, Wei Chen, Kai Xu [Paper (coming soon)] [Project Page] [Code] We present CGGT, a unified feed-forward framework that recovers structured curve cues from unposed, sparse images, integrating a geometry-aware transformer encoder with a curve-aware masked-attention module for cross-view instance association.
🏆 ECCV 2026 Oral	HoloTetSphere: Unified TetSphere Mesh Reconstruction for Physical Simulations Yaqiao Dai, Renjiao Yi, Zhirui Gao, Wei Chen, Kai Xu, Chenyang Zhu [arXiv] [Project Page (coming soon)] [Code] We introduce a novel representation that tightly couples tetrahedral mesh elements with Gaussian spheres, enabling both high-quality rendering and topology-adaptive optimization within a holistic framework.
PG 2025 CCF-B	BoxFusion: Reconstruction-Free Open-Vocabulary 3D Object Detection via Real-Time Multi-View Box Fusion Yuqing Lan, Chenyang Zhu, Zhirui Gao, Jiazhao Zhang, Yihan Cao, Renjiao Yi, Yijie Wang, Kai Xu [arXiv] [Project Page] [Code] We propose a novel reconstruction-free paradigm for online open-vocabulary 3D object detection, which models structural object layouts with desirable running and memory efficiency.
🏆 ICCV 2025 · CCF-A	Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction Zhirui Gao, Renjiao Yi, Yaqiao Dai, Xuening Zhu, Wei Chen, Chenyang Zhu, Kai Xu [arXiv] [Project Page] [Code] We present an end-to-end method for reconstructing 3D parametric curves directly from multi-view edge maps. Contrasting with the existing reconstruct-and-fit pipelines, our one-stage approach optimizes 3D parametric curves directly from 2D edge maps.
🏆 ICCV 2025 · CCF-A	Self-supervised Learning of Hybrid Part-aware 3D Representations of 2D Gaussians and Superquadrics Zhirui Gao, Renjiao Yi, Yuhang Huang, Wei Chen, Chenyang Zhu, Kai Xu [arXiv] [Project Page] [Code] We introduce PartGS, a self-supervised part-aware reconstruction framework that integrates 2D Gaussians and superquadrics to parse objects and scenes into an interpretable decomposition, leveraging multi-view image inputs to uncover 3D structural information.
IEEE TCSVT 2025 CCF-B	Generic Objects as Pose Probes for Few-shot View Synthesis Zhirui Gao, Renjiao Yi, Chenyang Zhu, Ke Zhuang, Wei Chen, Kai Xu [arXiv] [Project Page] [Code] We propose to utilize everyday objects, commonly found in both images and real life, as "pose probes" to tackle few-view (3~6 unposed images) NeRF reconstruction.
🏆 ICCV 2023 · CCF-A	2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds Minhao Li, Zheng Qin, Zhirui Gao, Renjiao Yi, Chenyang Zhu, Yulan Guo, Kai Xu [arXiv] [Project Page] [Code] The commonly adopted detect-then-match approach to registration finds difficulties in the cross-modality cases due to the incompatible keypoint detection and inconsistent feature description. We propose, 2D3D-MATR, a detection-free method for accurate and robust registration between images and point clouds.
🏆 CVPR 2023 · CCF-A	NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-view Images Yunfan Ye, Renjiao Yi, Zhirui Gao, Chenyang Zhu, Zhiping Cai, Kai Xu [arXiv] [Project Page] [Code] We study the problem of reconstructing 3D feature curves of an object from a set of calibrated multi-view images. To do so, we learn a neural implicit field representing the density distribution of