English
Related papers

Related papers: 3DGSNav: Enhancing Vision-Language Model Reasoning…

200 papers

Jointly estimating camera poses and mapping scenes from RGBD images is a fundamental task in simultaneous localization and mapping (SLAM). State-of-the-art methods employ 3D Gaussians to represent a scene, and render these Gaussians through…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Pengchong Hu , Zhizhong Han

We propose a method to enhance 3D Gaussian Splatting (3DGS)~\cite{Kerbl2023}, addressing challenges in initialization, optimization, and density control. Gaussian Splatting is an alternative for rendering realistic images while supporting…

Computer Vision and Pattern Recognition · Computer Science 2025-07-02 Xingjun Wang , Lianlei Shan

Vision-and-Language Navigation (VLN) requires an agent to ground language instructions to its own movement within a visual environment. While state-of-the-art methods leverage the reasoning capabilities of Vision-Language Models (VLMs) for…

Open-Vocabulary Object Navigation (OVON) requires an embodied agent to locate a language-specified target in unknown environments. Existing zero-shot methods often reason over dense frontier points under incomplete observations, causing…

Robotics · Computer Science 2026-03-31 Maoguo Gao , Zejun Zhu , Zhiming Sun , Zhengwei Ma , Longze Yuan , Zhongjing Ma , Zhigang Gao , Jinhui Zhang , Suli Zou

The emergence of 3D Gaussian Splatting (3DGS) has recently ignited a renewed wave of research in dense visual SLAM. However, existing approaches encounter challenges, including sensitivity to artifacts and noise, suboptimal selection of…

Robotics · Computer Science 2025-08-26 Wancai Zheng , Xinyi Yu , Jintao Rong , Linlin Ou , Yan Wei , Libo Zhou

Vision-and-Language Navigation (VLN) requires an embodied agent to ground complex natural-language instructions into long-horizon navigation in unseen environments. While Vision-Language Models (VLMs) offer strong 2D semantic understanding,…

Robotics · Computer Science 2026-03-19 Zihao Xin , Wentong Li , Yixuan Jiang , Ziyuan Huang , Bin Wang , Piji Li , Jianke Zhu , Jie Qin , Shengjun Huang

Injecting semantics into 3D Gaussian Splatting (3DGS) has recently garnered significant attention. While current approaches typically distill 3D semantic features from 2D foundational models (e.g., CLIP and SAM) to facilitate novel view…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Wenbo Zhang , Lu Zhang , Ping Hu , Liqian Ma , Yunzhi Zhuge , Huchuan Lu

We present LatentAM, an online 3D Gaussian Splatting (3DGS) mapping framework that builds scalable latent feature maps from streaming RGB-D observations for open-vocabulary robotic perception. Instead of distilling high-dimensional…

Robotics · Computer Science 2026-02-16 Junwoon Lee , Yulun Tian

We present Splat-Nav, a real-time robot navigation pipeline for Gaussian Splatting (GSplat) scenes, a powerful new 3D scene representation. Splat-Nav consists of two components: 1) Splat-Plan, a safe planning module, and 2) Splat-Loc, a…

In this study, we present an end-to-end pipeline capable of converting drone-captured video streams into high-fidelity 3D reconstructions with minimal latency. Unmanned aerial vehicles (UAVs) are extensively used in aerial real-time…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Christos Maikos , Georgios Angelidis , Georgios Th. Papadopoulos

3D Gaussian Splatting has recently gained traction for its efficient training and real-time rendering. While its vanilla representation is mainly designed for view synthesis, recent works extended it to scene understanding with language…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Siyun Liang , Sen Wang , Kunyi Li , Michael Niemeyer , Stefano Gasperini , Hendrik P. A. Lensch , Nassir Navab , Federico Tombari

Although 3D Gaussian Splatting (3D-GS) achieves efficient rendering for novel view synthesis, extending it to dynamic scenes still results in substantial memory overhead from replicating Gaussians across frames. To address this challenge,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Chun-Tin Wu , Jun-Cheng Chen

We present SGS-SLAM, the first semantic visual SLAM system based on Gaussian Splatting. It incorporates appearance, geometry, and semantic features through multi-channel optimization, addressing the oversmoothing limitations of neural…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Mingrui Li , Shuhong Liu , Heng Zhou , Guohao Zhu , Na Cheng , Tianchen Deng , Hongyu Wang

3D Gaussian Splatting (3DGS) has become an emerging tool for dynamic scene reconstruction. However, existing methods focus mainly on extending static 3DGS into a time-variant representation, while overlooking the rich motion information…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Zhiyang Guo , Wengang Zhou , Li Li , Min Wang , Houqiang Li

3D Gaussian Splatting (3DGS) has emerged as a leading approach for high-quality novel view synthesis, with numerous variants extending its applicability to a broad spectrum of 3D and 4D scene reconstruction tasks. Despite its success, the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Yiming Wang , Shaofei Wang , Marko Mihajlovic , Siyu Tang

Photographs captured in unstructured tourist environments frequently exhibit variable appearances and transient occlusions, challenging accurate scene reconstruction and inducing artifacts in novel view synthesis. Although prior approaches…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Jiacong Xu , Yiqun Mei , Vishal M. Patel

3D Gaussian Splatting (3DGS) is a recent approach for scene rendering. Although primarily designed for view synthesis, its potential for scene understanding tasks remains underexplored. In this work, we conduct a comparative evaluation of…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Julia Farganus , Krzysztof Żurawicki , Arkadiusz Gaweł , Weronika Jakubowska , Halina Kwaśnicka

Vision-language Navigation (VLN) requires an agent to understand visual observations and language instructions to navigate in unseen environments. Most existing approaches rely on static scene assumptions and struggle to generalize in…

Robotics · Computer Science 2026-03-24 Xiangchen Liu , Hanghan Zheng , Jeil Jeong , Minsung Yoon , Lin Zhao , Zhide Zhong , Haoang Li , Sung-Eui Yoon

To enable AI agents to interact seamlessly with both humans and 3D environments, they must not only perceive the 3D world accurately but also align human language with 3D spatial representations. While prior work has made significant…

Artificial Intelligence · Computer Science 2025-09-26 Saimouli Katragadda , Cho-Ying Wu , Yuliang Guo , Xinyu Huang , Guoquan Huang , Liu Ren

Accurate object segmentation is crucial for high-quality scene understanding in the 3D vision domain. However, 3D segmentation based on 3D Gaussian Splatting (3DGS) struggles with accurately delineating object boundaries, as Gaussian…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Jiaxin Zhang , Junjun Jiang , Youyu Chen , Kui Jiang , Xianming Liu