中文
相关论文

相关论文: Taming the Light: Illumination-Invariant Semantic …

200 篇论文

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…

计算机视觉与模式识别 · 计算机科学 2024-11-26 Mingrui Li , Shuhong Liu , Heng Zhou , Guohao Zhu , Na Cheng , Tianchen Deng , Hongyu Wang

We present a mapping system capable of constructing detailed instance-level semantic models of room-sized indoor environments by means of an RGB-D camera. In this work, we integrate deep-learning-based instance segmentation and…

机器人学 · 计算机科学 2019-11-22 Dinh-Cuong Hoang , Todor Stoyanov , Achim J. Lilienthal

3D Gaussian Splatting (3DGS) has recently emerged as a powerful representation of geometry and appearance for dense Simultaneous Localization and Mapping (SLAM). Through rapid, differentiable rasterization of 3D Gaussians, many 3DGS SLAM…

机器人学 · 计算机科学 2025-03-25 Xulang Liu , Ning Tan

The bundle of geometry and appearance in computer vision has proven to be a promising solution for robots across a wide variety of applications. Stereo cameras and RGB-D sensors are widely used to realise fast 3D reconstruction and…

计算机视觉与模式识别 · 计算机科学 2016-11-15 Xuanpeng Li , Rachid Belaroussi

Recent advances in 3D Gaussian Splatting (3DGS) have enabled RGB-only SLAM systems to achieve high-fidelity scene representation. However, the heavy reliance of existing systems on photometric rendering loss for camera tracking undermines…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Zhen Tan , Xieyuanli Chen , Lei Feng , Yangbing Ge , Shuaifeng Zhi , Jiaxiong Liu , Dewen Hu

Most of the existing visual SLAM methods heavily rely on a static world assumption and easily fail in dynamic environments. Some recent works eliminate the influence of dynamic objects by introducing deep learning-based semantic information…

机器人学 · 计算机科学 2022-01-10 Tete Ji , Chen Wang , Lihua Xie

Visual SLAM in dynamic environments remains challenging, as several existing methods rely on semantic filtering that only handles known object classes, or use fixed robust kernels that cannot adapt to unknown moving objects, leading to…

机器人学 · 计算机科学 2025-10-21 João Carlos Virgolino Soares , Gabriel Fischer Abati , Claudio Semini

Current techniques in Visual Simultaneous Localization and Mapping (VSLAM) estimate camera displacement by comparing image features of consecutive scenes. These algorithms depend on scene continuity, hence requires frequent camera inputs.…

机器人学 · 计算机科学 2024-01-25 Mingyang Li , Yue Ma , Qinru Qiu

Robust Visual SLAM (vSLAM) is essential for autonomous systems operating in real-world environments, where challenges such as dynamic objects, low texture, and critically, varying illumination conditions often degrade performance. Existing…

The assumption of scene rigidity is typical in SLAM algorithms. Such a strong assumption limits the use of most visual SLAM systems in populated real-world environments, which are the target of several relevant applications like service…

计算机视觉与模式识别 · 计算机科学 2018-08-16 Berta Bescos , José M. Fácil , Javier Civera , José Neira

The research in dense online 3D mapping is mostly focused on the geometrical accuracy and spatial extent of the reconstructions. Their color appearance is often neglected, leading to inconsistent colors and noticeable artifacts. We rectify…

计算机视觉与模式识别 · 计算机科学 2018-04-23 Sergey V. Alexandrov , Johann Prankl , Michael Zillich , Markus Vincze

Visual Simultaneous Localization and Mapping (SLAM) plays a vital role in real-time localization for autonomous systems. However, traditional SLAM methods, which assume a static environment, often suffer from significant localization drift…

机器人学 · 计算机科学 2025-07-30 Haolan Zhang , Thanh Nguyen Canh , Chenghao Li , Nak Young Chong

Visual Simultaneous Localization and Mapping (vSLAM) is a widely used technique in robotics and computer vision that enables a robot to create a map of an unfamiliar environment using a camera sensor while simultaneously tracking its…

计算机视觉与模式识别 · 计算机科学 2023-05-10 Yasaman Haghighi , Suryansh Kumar , Jean-Philippe Thiran , Luc Van Gool

Robot perception under low light or high dynamic range is usually improved downstream - via more robust feature extraction, image enhancement, or closed-loop exposure control. However, all of these approaches are limited by the image…

机器人学 · 计算机科学 2026-02-19 Yash Turkar , Shekoufeh Sadeghi , Karthik Dantu

We present a dense simultaneous localization and mapping (SLAM) method that uses 3D Gaussians as a scene representation. Our approach enables interactive-time reconstruction and photo-realistic rendering from real-world single-camera RGBD…

计算机视觉与模式识别 · 计算机科学 2024-03-25 Vladimir Yugay , Yue Li , Theo Gevers , Martin R. Oswald

Achieving real-time Simultaneous Localization and Mapping (SLAM) based on 3D Gaussian splatting (3DGS) in large-scale real-world environments remains challenging, as existing methods still struggle to jointly achieve low-latency pose…

Simultaneous Localization and Mapping (SLAM) is one of the most essential techniques in many real-world robotic applications. The assumption of static environments is common in most SLAM algorithms, which however, is not the case for most…

机器人学 · 计算机科学 2022-05-17 Han Wang , Jing Ying Ko , Lihua Xie

Existing visual SLAM approaches are sensitive to illumination, with their precision drastically falling in dark conditions due to feature extractor limitations. The algorithms currently used to overcome this issue are not able to provide…

We present a real-time tracking SLAM system that unifies efficient camera tracking with photorealistic feature-enriched mapping using 3D Gaussian Splatting (3DGS). Our main contribution is integrating dense feature rasterization into the…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Christopher Thirgood , Oscar Mendez , Erin Ling , Jon Storey , Simon Hadfield

Emerging 3D scene representations, such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), have demonstrated their effectiveness in Simultaneous Localization and Mapping (SLAM) for photo-realistic rendering, particularly…

计算机视觉与模式识别 · 计算机科学 2025-08-11 Peng Wang , Lingzhe Zhao , Yin Zhang , Shiyu Zhao , Peidong Liu