Zinan Lv
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zinan Lv has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Chunxiang Wang
Shanghai Jiao Tong University
2 shared publications - Ming-Hsuan Yang
University of California, Merced, USA
2 shared publications - Yeqiang Qian
Shanghai Jiao Tong University
2 shared publications - Feng Zhou
Beijing University of Posts and Telecommunications, Beijing, China
1 shared publication - Jianqin Yin
Beijing University of Posts and Telecommunications, Beijing, China
1 shared publication - Peng Sun
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
GeoWeave: Learning Reliable Cross-View Dependencies for Feed-Forward 3D Reconstruction
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessGeoWeave: Learning Reliable Cross-View Dependencies for Feed-Forward 3D Reconstruction
- 1 August 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (8) , 9835-9842
A Ground-Centric UAV-UGV Cooperative System for Autonomous Launch and Recovery
- 1 August 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (8) , 9835-9842
A Ground-Centric UAV-UGV Cooperative System for Autonomous Launch and Recovery
- 1 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (2) , 1754-1766
Structure-Guided Memory-Efficient 3D Gaussians for Large-Scale Reconstruction
3D reconstruction is a critical technology with significant implications for applications such as urban planning, autonomous driving, and virtual reality. Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated impressive results in small-scale scenes, achieving high-quality reconstructions with real-time rendering capabilities. However, when applied to large-scale scenes, existing 3DGS methods face significant challenges due to the exponential growth of model size, often exceeding the memory capacity of consumer-grade GPUs and making training and rendering infeasible. In this paper, we propose a structure-guided memory-efficient 3DGS framework that uses only half the memory of current large-scale 3DGS methods while maintaining state-of-the-art reconstruction accuracy. Specifically, we introduce a structure-guided density control mechanism that uses a heuristic approach to split Gaussian ellipsoids in challenging regions and optimizes their attributes during densification, significantly reducing memory storage requirements while preserving structural details with fewer ellipsoids. Moreover, we propose a novel structure loss to supervise the learning of scene structural information, enabling the model to better capture and preserve geometric details such as straight lines and edges, further enhancing reconstruction accuracy. We also propose the largest known drone dataset for 3D reconstruction, comprising over 10,000 high-resolution images covering more than 2.5 million square meters. Extensive experiments on multiple benchmark datasets and our proposed dataset demonstrate that our new method is highly memory-efficient with high accuracy.
- 1 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (2) , 1754-1766
Structure-Guided Memory-Efficient 3D Gaussians for Large-Scale Reconstruction
3D reconstruction is a critical technology with significant implications for applications such as urban planning, autonomous driving, and virtual reality. Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated impressive results in small-scale scenes, achieving high-quality reconstructions with real-time rendering capabilities. However, when applied to large-scale scenes, existing 3DGS methods face significant challenges due to the exponential growth of model size, often exceeding the memory capacity of consumer-grade GPUs and making training and rendering infeasible. In this paper, we propose a structure-guided memory-efficient 3DGS framework that uses only half the memory of current large-scale 3DGS methods while maintaining state-of-the-art reconstruction accuracy. Specifically, we introduce a structure-guided density control mechanism that uses a heuristic approach to split Gaussian ellipsoids in challenging regions and optimizes their attributes during densification, significantly reducing memory storage requirements while preserving structural details with fewer ellipsoids. Moreover, we propose a novel structure loss to supervise the learning of scene structural information, enabling the model to better capture and preserve geometric details such as straight lines and edges, further enhancing reconstruction accuracy. We also propose the largest known drone dataset for 3D reconstruction, comprising over 10,000 high-resolution images covering more than 2.5 million square meters. Extensive experiments on multiple benchmark datasets and our proposed dataset demonstrate that our new method is highly memory-efficient with high accuracy.