7 papers
SONG: A Photorealistic 3D Gaussian Simulation Platform for Benchmarking Social Navigation
Weiqi Huang, Dianyi Yang, Jiaxin Li +4
The paper presents SONG, a photorealistic 3D simulation platform that uses 3D Gaussian splatting to generate realistic visual scenes and moving human avatars for evaluating vision‑…
CubifyGS: Object-Centric 3D Gaussian Splatting for Lifelong Dynamic Scene Maintenance
Bohan Ren, Dianyi Yang, Shiyang Liu +5
Lifelong scene mapping under rigid object rearrangement remains a fundamental challenge in robotics. While 3D Gaussian Splatting (3DGS) enables high-fidelity modeling, primitive-le…
OpenGS-Fusion: Open-Vocabulary Dense Mapping with Hybrid 3D Gaussian Splatting for Refined Object-Level Understanding
Dianyi Yang, Xihan Wang, Yu Gao +4
Recent advancements in 3D scene understanding have made significant strides in enabling interaction with scenes using open-vocabulary queries, particularly for VR/AR and robotic ap…
Automated 3D-GS Registration and Fusion via Skeleton Alignment and Gaussian-Adaptive Features
Shiyang Liu, Dianyi Yang, Yu Gao +3
In recent years, 3D Gaussian Splatting (3D-GS)-based scene representation demonstrates significant potential in real-time rendering and training efficiency. However, most existing…
DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery
Jiadong Tang, Yu Gao, Dianyi Yang +3
Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rende…
GaussianGraph: 3D Gaussian-based Scene Graph Generation for Open-world Scene Understanding
Xihan Wang, Dianyi Yang, Yu Gao +3
Recent advancements in 3D Gaussian Splatting(3DGS) have significantly improved semantic scene understanding, enabling natural language queries to localize objects within a scene. H…