Pages
- 1
- 2
- document
-
Forouzandeh Shahraki, N. (author), Brembilla, E. (author), Nan, L. (author), Stoter, J.E. (author), Jakubiec, Alstan (author)Optimizing the built environment via simulations of building models hinges on standardizing data acquisition. In this research, we put forward distinct levels of detail for geometry and material inputs, specifically tailored for indoor daylight applications. We primarily focus on understanding the uncertainties arising from imprecise...journal article 2024
- document
-
Forouzandeh Shahraki, N. (author), Brembilla, E. (author), Stoter, J.E. (author), Nan, L. (author)3D modeling of indoor spaces is a prerequisite for daylight simulation, and the accuracy of the 3D models has a significant impact on the simulation. The goal of this study was to quantify the errors caused by modeling indoor spaces at different accuracy levels to find the optimal balance between the reliability of the results and labor...conference paper 2024
- document
-
Li, Minglei (author), Peng, Shu (author), Nan, L. (author)We propose a concept of hybrid geometry sets for registering cross-source geometric data. Specifically, our method focuses on the coarse registration of geometric data obtained from laser scanning and photogrammetric reconstruction. Due to different characteristics (e.g., variations in noise levels, density, and scales), achieving accurate...journal article 2024
- document
-
Gu, Lipeng (author), Yan, Xuefeng (author), Nan, L. (author), Zhu, Dingkun (author), Chen, Honghua (author), Wang, Weiming (author), Wei, Mingqiang (author)The conventional wisdom in point cloud analysis predominantly explores 3D geometries. It is often achieved through the introduction of intricate learnable geometric extractors in the encoder or by deepening networks with repeated blocks. However, these methods contain a significant number of learnable parameters, resulting in substantial...journal article 2024
- document
-
Gao, W. (author), Nan, L. (author), Boom, Bas (author), Ledoux, H. (author)We introduce a novel deep learning-based framework to interpret 3D urban scenes represented as textured meshes. Based on the observation that object boundaries typically align with the boundaries of planar regions, our framework achieves semantic segmentation in two steps: planarity-sensible over-segmentation followed by semantic...journal article 2023
- document
-
Zaffar, M. (author), Nan, L. (author), Kooij, J.F.P. (author)Visual place recognition (VPR) is an image-based localization method that estimates the camera location of a query image by retrieving the most similar reference image from a map of geo-tagged reference images. In this work, we look into two fundamental bottlenecks for its localization accuracy: 1) reference map sparseness and 2) viewpoint...journal article 2023
- document
-
Ibrahimli, N. (author), Ledoux, H. (author), Kooij, J.F.P. (author), Nan, L. (author)We propose an enhancement module called depth discontinuity learning (DDL) for learning-based multi-view stereo (MVS) methods. Traditional methods are known for their accuracy but struggle with completeness. While recent learning-based methods have improved completeness at the cost of accuracy, our DDL approach aims to improve accuracy while...journal article 2023
- document
-
Huang, J. (author), Stoter, J.E. (author), Nan, L. (author)Symmetry widely exists in nature and man-made shapes, but it is unavoidably distorted during the process of growth, design, digitalization, and reconstruction steps. To enhance symmetry, traditional methods follow the detect-then-symmetrize paradigm, which is sensitive to noise in the detection phase, resulting in ambiguities for the...journal article 2023
- document
-
Yang, Z. (author), Ye, Qin (author), Stoter, J.E. (author), Nan, L. (author)Continuous implicit representations can flexibly describe complex 3D geometry and offer excellent potential for 3D point cloud analysis. However, it remains challenging for existing point-based deep learning architectures to leverage the implicit representations due to the discrepancy in data structures between implicit fields and point...journal article 2023
- document
-
Wang, Xufei (author), Yang, Z. (author), Cheng, Xiaojun (author), Stoter, J.E. (author), Xu, Wenbing (author), Wu, Zhenlun (author), Nan, L. (author)Registering point clouds of forest environments is an essential prerequisite for LiDAR applications in precision forestry. State-of-the-art methods for forest point cloud registration require the extraction of individual tree attributes, and they have an efficiency bottleneck when dealing with point clouds of real-world forests with dense...journal article 2023
- document
-
Huang, J. (author), Stoter, J.E. (author), Peters, R.Y. (author), Nan, L. (author)We present a fully automatic approach for reconstructing compact 3D building models from large-scale airborne point clouds. A major challenge of urban reconstruction from airborne LiDAR point clouds lies in that the vertical walls are typically missing. Based on the observation that urban buildings typically consist of planar roofs connected...journal article 2022
- document
-
Xing, Xuejun (author), Guo, Jianwei (author), Nan, L. (author), Gu, Qingyi (author), Zhang, Xiaopeng (author), Yan, Dong Ming (author)The point pair feature (PPF) is widely used in industrial applications for estimating 6D poses of known objects from unrecognized point clouds. The key to the success of PPF matching is to establish correct 3D correspondences between the object and the scene, i.e., finding as many valid similar point pairs as possible. Thus, a set of...journal article 2022
- document
-
Chen, Z. (author), Ledoux, H. (author), Khademi, S. (author), Nan, L. (author)While three-dimensional (3D) building models play an increasingly pivotal role in many real-world applications, obtaining a compact representation of buildings remains an open problem. In this paper, we present a novel framework for reconstructing compact, watertight, polygonal building models from point clouds. Our framework comprises three...journal article 2022
- document
-
Xu, Yabin (author), Nan, L. (author), Zhou, Laishui (author), Wang, Jun (author), Wang, C.C. (author)Reconstruction of high-fidelity 3D objects or scenes is a fundamental research problem. Recent advances in RGB-D fusion have demonstrated the potential of producing 3D models from consumer-level RGB-D cameras. However, due to the discrete nature and limited resolution of their surface representations (e.g., point or voxel based), existing...journal article 2022
- document
-
Li, M. (author), Li, J. (author), Tamayo, A. (author), Nan, L. (author)This paper presents a method for multiple object tracking (MOT) in video streams. The method incorporates the prediction of physical locations of people into a tracking-by-detection paradigm. We predict the trajectories of people on an estimated ground plane and apply a learning-based network to extract the appearance features across frames....journal article 2022
- document
-
Lin, Yan (author), Qian, Chengduo (author), Shi, Jingtao (author), Zhang, Yuzhen (author), Ren, S. (author), Nan, Guozhi (author), Kong, Xiangjun (author), Fan, Weiyu (author)Compared with traditional asphalt, emulsified asphalt occurs to be a better low-temperature usability and environmental adaptability, which can reduce environmental pollution and energy consuming during road construction. The low-temperature ductility is a very important indicator to evaluate the environmental adaptability of emulsified asphalt....journal article 2022
- document
-
Du, S. (author), Ibrahimli, N. (author), Stoter, J.E. (author), Kooij, J.F.P. (author), Nan, L. (author)Feedforward fully convolutional neural networks currently dominate in semantic segmentation of 3D point clouds. Despite their great success, they suffer from the loss of local information at low-level layers, posing significant challenges to accurate scene segmentation and precise object boundary delineation. Prior works either address this...conference paper 2022
- document
-
Chen, Jiazhou (author), Xu, Yanghui (author), Lu, Shufang (author), Liang, Ronghua (author), Nan, L. (author)We present a novel 3-D instance segmentation framework for multiview stereo (MVS) buildings in urban scenes. Unlike existing works focusing on semantic segmentation of urban scenes, the emphasis of this work lies in detecting and segmenting 3-D building instances even if they are attached and embedded in a large and imprecise 3-D surface model....journal article 2022
- document
-
Fan, Guangpeng (author), Xu, Zhenyu (author), Wang, Jinhu (author), Nan, L. (author), Xiao, Huijie (author), Xin, Zhiming (author), Chen, Feixiang (author)Complexity of forest structure is an important factor contributing to uncertainty in aboveground biomass estimates. In this study, we present a new method for reducing uncertainty in forest aboveground biomass (AGB) estimation based on plot-level terrestrial laser scanner (TLS) point clouds reconstruction. The method estimates the total AGB...journal article 2022
- document
-
Nan, L. (author)Easy3D is an open-source library for 3D modeling, geometry processing, and rendering. It is implemented in C++ and designed with an emphasis on simplicity (i.e., processing and visualizing 3D data can be achieved by few lines of API calls). The contributions of Easy3D are threefold: (1) efficient data structures for representing common 3D data ...journal article 2021
Pages
- 1
- 2