66 skills found · Page 1 of 3
FuxiCV / 3D Face GCNsTowards High-Fidelity 3D Face Reconstruction from In-the-Wild Images Using Graph Convolutional Networks, CVPR 2020
humansensinglab / Hamba[NeurIPS 2024] Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba
chenzhaiyu / PolygnnPolyGNN: Polyhedron-based graph neural network for 3D building reconstruction from point clouds [ISPRS 2024]
rimsa / CFGgrindA dynamic control flow graph (CFG) reconstruction plugin for valgrind.
JinheonBaek / GMTOfficial Code Repository for the paper "Accurate Learning of Graph Representations with Graph Multiset Pooling" (ICLR 2021)
xuewenyuan / TGRNetTGRNet: A Table Graph Reconstruction Network for Table Structure Recognition
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.
Kali-Hac / TranSG[CVPR-2023] Official Codes for "TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning with Structure-Trajectory Prompted Reconstruction for Person Re-Identification"
facebookresearch / 3D Vision And TouchWhen told to understand the shape of a new object, the most instinctual approach is to pick it up and inspect it with your hand and eyes in tandem. Here, touch provides high fidelity localized information while vision provides complementary global context. However, in 3D shape reconstruction, the complementary fusion of visual and haptic modalities remains largely unexplored. In this paper, we study this problem and present an effective chart-based approach to fusing vision and touch, which leverages advances in graph convolutional networks. To do so, we introduce a dataset of simulated touch and vision signals from the interaction between a robotic hand and a large array of 3D objects. Our results show that (1) leveraging both vision and touch signals consistently improves single-modality baselines, especially when the object is occluded by the hand touching it; (2) our approach outperforms alternative modality fusion methods and strongly benefits from the proposed chart-based structure; (3) reconstruction quality boosts with the number of grasps provided; and (4) the touch information not only enhances the reconstruction at the touch site but also extrapolates to its local neighborhood.
bnusss / GGNGumbel Graph Network (GGN) : A General Deep Learning Framework for Network Reconstruction
JiaxiangZheng / DeformationGraphA implemetation of deformation graph which was widely used in mesh deformation and non-rigid reconstruction
Graph-COM / GAD NR[WSDM 2024] GAD-NR : Graph Anomaly Detection via Neighborhood Reconstruction
harryjo97 / EHGNNOfficial Code Repository for the paper "Edge Representation Learning with Hypergraphs" (NeurIPS 2021)
Hero941215 / Fast Lio Sam LoopFast lio with loop closing function. the Transform between map coordinate to Odom coordinate is maintained and used to correct the FAST-LIO pose to the map system, providing initial pose-graph. Therefore, Fast-lio2's ikd tree does not require reconstruction, ensuring that the front-end can always run efficiently.
peraro / FiniteflowMultivariate functional reconstruction using finite fields and dataflow graphs.
raphaelsulzer / Dgnn[SGP 2021] Scalable Surface Reconstruction with Delaunay-Graph Neural Networks
OlegKonings / CUDA Floyd Warshall CUDA implementation of the Floyd-Warshall All pairs shortest path graph algorithm(with path reconstruction)
Iris-cyy / SG NeRFOfficial implementation of "SG-NeRF: Neural Surface Reconstruction with Scene Graph Optimization" (ECCV 2024)
dubssieg / PancatPangenome graphs visualisation, distance computing, reconstruction of sequences and other utility functions
zczcwh / GTRSThe project is an official implementation of our paper "A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose".
