中文
相关论文

相关论文: Hestia: Voxel-Face-Aware Hierarchical Next-Best-Vi…

200 篇论文

Path-planning algorithms are an important part of a wide variety of robotic applications, such as mobile robot navigation and robot arm manipulation. However, in large search spaces in which local traps may exist, it remains challenging to…

机器学习 · 计算机科学 2019-08-12 Yuka Ariki , Takuya Narihira

Recovery of an underlying scene geometry from multiview images stands as a long-time challenge in computer vision research. The recent promise leverages neural implicit surface learning and differentiable volume rendering, and achieves both…

计算机视觉与模式识别 · 计算机科学 2023-03-02 Zhihao Liang , Zhangjin Huang , Changxing Ding , Kui Jia

We consider the problem of planning views for a robot to acquire images of an object for visual inspection and reconstruction. In contrast to offline methods which require a 3D model of the object as input or online methods which rely on…

机器人学 · 计算机科学 2019-10-07 Selim Engin , Eric Mitchell , Daewon Lee , Volkan Isler , Daniel D. Lee

We introduce the first learning-based reconstructability predictor to improve view and path planning for large-scale 3D urban scene acquisition using unmanned drones. In contrast to previous heuristic approaches, our method learns a model…

图形学 · 计算机科学 2022-09-22 Yilin Liu , Liqiang Lin , Yue Hu , Ke Xie , Chi-Wing Fu , Hao Zhang , Hui Huang

Recent advances in neural scene representations have led to unprecedented quality in 3D reconstruction and view synthesis. Despite achieving high-quality results for common benchmarks with curated data, outputs often degrade for data that…

Surface reconstruction is fundamental to computer vision and graphics, enabling applications in 3D modeling, mixed reality, robotics, and more. Existing approaches based on volumetric rendering obtain promising results, but optimize on a…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Yueh-Cheng Liu , Lukas Höllein , Matthias Nießner , Angela Dai

The generation of high-fidelity view synthesis is essential for robotic navigation and interaction but remains challenging, particularly in indoor environments and real-time scenarios. Existing techniques often require significant…

计算机视觉与模式识别 · 计算机科学 2024-12-05 Sen Wang , Qing Cheng , Stefano Gasperini , Wei Zhang , Shun-Cheng Wu , Niclas Zeller , Daniel Cremers , Nassir Navab

We present VISTA (Viewpoint-based Image selection with Semantic Task Awareness), an active exploration method for robots to plan informative trajectories that improve 3D map quality in areas most relevant for task completion. Given an…

Novel view synthesis has seen major advances in recent years, with 3D Gaussian splatting offering an excellent level of visual quality, fast training and real-time rendering. However, the resources needed for training and rendering…

计算机视觉与模式识别 · 计算机科学 2024-06-19 Bernhard Kerbl , Andréas Meuleman , Georgios Kopanas , Michael Wimmer , Alexandre Lanvin , George Drettakis

Voxel coloring is a popular method of reconstructing a three-dimensional surface model from a set of calibrated 2D images. However, the reconstruction quality is largely dependent on a thresholding procedure allowing the authors to decide,…

计算机视觉与模式识别 · 计算机科学 2018-09-18 Mohamed Chafik Bakkay , Walid Barhoumi , Ezzeddine Zagrouba

Motivated by the advances in 3D sensing technology and the spreading of low-cost robotic platforms, 3D object reconstruction has become a common task in many areas. Nevertheless, the selection of the optimal sensor pose that maximizes the…

计算机视觉与模式识别 · 计算机科学 2021-01-27 Miguel Mendoza , J. Irving Vasquez-Gomez , Hind Taud , Luis Enrique Sucar , Carolina Reta

Humans are in constant contact with the world as they move through it and interact with it. This contact is a vital source of information for understanding 3D humans, 3D scenes, and the interactions between them. In fact, we demonstrate…

计算机视觉与模式识别 · 计算机科学 2022-03-30 Hongwei Yi , Chun-Hao P. Huang , Dimitrios Tzionas , Muhammed Kocabas , Mohamed Hassan , Siyu Tang , Justus Thies , Michael J. Black

Repeated plant monitoring is essential for tracking crop growth, and 3D reconstruction enables consistent comparison across monitoring sessions. However, rebuilding a 3D model from scratch in every session is costly and overlooks…

机器人学 · 计算机科学 2026-03-24 Sicong Pan , Luca Lobefaro , Moein Taherkhani , Xuying Huang , Rohit Menon , Cyrill Stachniss , Maren Bennewitz

Next Best View (NBV) algorithms aim to maximize 3D scene acquisition quality using minimal resources, e.g. number of acquisitions, time taken, or distance traversed. Prior methods often rely on coverage maximization as a proxy for…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Noah Frahm , Dongxu Zhao , Andrea Dunn Beltran , Ron Alterovitz , Jan-Michael Frahm , Junier Oliva , Roni Sengupta

Active 3D reconstruction enables an agent to autonomously select viewpoints to efficiently obtain accurate and complete scene geometry, rather than passively reconstructing scenes from pre-collected images. However, existing active…

计算机视觉与模式识别 · 计算机科学 2025-12-08 Tianling Xu , Shengzhe Gan , Leslie Gu , Yuelei Li , Fangneng Zhan , Hanspeter Pfister

Transformer-based models, capable of learning better global dependencies, have recently demonstrated exceptional representation learning capabilities in computer vision and medical image analysis. Transformer reformats the image into…

A popular approach for constructing bird's-eye-view (BEV) representation in 3D detection is to lift 2D image features onto the viewing frustum space based on explicitly predicted depth distribution. However, depth distribution can only…

计算机视觉与模式识别 · 计算机科学 2024-01-12 Zaibin Zhang , Yuanhang Zhang , Lijun Wang , Yifan Wang , Huchuan Lu

Neural surface reconstruction aims to reconstruct accurate 3D surfaces based on multi-view images. Previous methods based on neural volume rendering mostly train a fully implicit model with MLPs, which typically require hours of training…

计算机视觉与模式识别 · 计算机科学 2023-08-15 Tong Wu , Jiaqi Wang , Xingang Pan , Xudong Xu , Christian Theobalt , Ziwei Liu , Dahua Lin

Actively planning sensor views during object reconstruction is crucial for autonomous mobile robots. An effective method should be able to strike a balance between accuracy and efficiency. In this paper, we propose a seamless integration of…

机器人学 · 计算机科学 2024-05-29 Dongyu Yan , Jianheng Liu , Fengyu Quan , Haoyao Chen , Mengmeng Fu

Inferring 3D locations and shapes of multiple objects from a single 2D image is a long-standing objective of computer vision. Most of the existing works either predict one of these 3D properties or focus on solving both for a single object.…

计算机视觉与模式识别 · 计算机科学 2021-11-08 Feng Liu , Xiaoming Liu