Wantong Duan — accepted AI-conference papers

2026

Urban-GS: A Unified 3D Gaussian Splatting Framework for Compact and High-Fidelity Aerial-to-Street Reconstruction

Meng Wang, Changqun Xia, Yuze Wang, Junyi Wang, Wantong Duan, Xinxiong Xie +1

CVPR 2026

Recently, 3D Gaussian Splatting (3DGS) has revolutionized radiance field reconstruction, enabling efficient and high-fidelity novel view synthesis. However, seamless integration of both aerial and street view images to model urban scenes remains a significant challenge for 3DGS. This joint setting s

Cited by 0 Source ↗Scholar ↗

2025

3D Gaussian Splatting based Scene-independent Relocalization with Unidirectional and Bidirectional Feature Fusion

Junyi Wang, Yuze Wang, Wantong Duan, Meng Wang, Yue Qi

NeurIPS 2025poster

Visual localization is a critical component across various domains. The recent emergence of novel scene representations, such as 3D Gaussian Splatting (3D GS), introduces new opportunities for advancing localization pipelines. In this paper, we propose a novel 3D GS-based framework for RGB based, sc…

Cited by 0 Source ↗Scholar ↗