11 skills found
hku-mars / ImMeshImMesh: An Immediate LiDAR Localization and Meshing Framework
lab-sun / SLAMesh[ICRA 2023] SLAMesh: Real-time LiDAR Simultaneous Localization and Meshing
RuanJY / SLAMeshICRA2023, A real-time LiDAR simultaneous localization and meshing method.
PRBonn / Range MclRange Image-based LiDAR Localization for Autonomous Vehicles Using Mesh Maps (chen2021icra)
uos / RmclMobile Robot Localization in 3D Triangle Meshes & Geometric Scene Graphs
facebookresearch / VCMeshConvLearning latent representations of registered meshes is useful for many 3D tasks. Techniques have recently shifted to neural mesh autoencoders. Although they demonstrate higher precision than traditional methods, they remain unable to capture fine-grained deformations. Furthermore, these methods can only be applied to a template-specific surface mesh, and is not applicable to more general meshes, like tetrahedrons and non-manifold meshes. While more general graph convolution methods can be employed, they lack performance in reconstruction precision and require higher memory usage. In this paper, we propose a non-template-specific fully convolutional mesh autoencoder for arbitrary registered mesh data. It is enabled by our novel convolution and (un)pooling operators learned with globally shared weights and locally varying coefficients which can efficiently capture the spatially varying contents presented by irregular mesh connections. Our model outperforms state-of-the-art methods on reconstruction accuracy. In addition, the latent codes of our network are fully localized thanks to the fully convolutional structure, and thus have much higher interpolation capability than many traditional 3D mesh generation models.
aldehydecho / ConvMeshCode for "Mesh-based Autoencoders for Localized Deformation Component Analysis", AAAI 2018
v-pnk / CadlocBenchmark for visual localization on imperfect 3D mesh models from the Internet
Fidentis / AnalystFidentis Analyst a target-orientated user-friendly computer interface for processing 3D meshes of human faces. The program enables a variety of 3D facial morphological analyses designed for forensic purposes, such as 3D facial composite construction, automated landmark localization, face-to-face comparison and analysis of facial morphological variation via batch processing.
botforge / HGMM PointCloudsUsing Hierarchical Gaussian Mixture Models on Point Cloud Data for Registration, Localization & Meshing
codearxiv / SurfMeshSmoothSurface triangle mesh smoothing w.r.t. vertex normals to preserve surface curvature. Runs parallel on OpenMP or CUDA if available. Vertex indices are reordered s.t. they are localized into patches to improve CUDA blocking into shared memory & spatial cache locality.
