3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning
We propose a method for generalizing deep learning for 3D point cloud registration on new, totally different datasets. It is based on two components, MS-SVConv and UDGE. Using Multi-Scale Sparse Voxel Convolution, MS-SVConv is a fast deep neural network that outputs the descriptors from point clouds for 3D registration between two scenes. UDGE is an algorithm for transferring deep networks on unknown datasets in a unsupervised way. The interest of the proposed method appears while using the two components, MS-SVConv and UDGE, together as a whole, which leads to state-of-the-art results on real world registration datasets such as 3DMatch, ETH and TUM. The code is publicly available at https://github.com/humanpose1/MS-SVConv .
Code (1)
Tasks
Point Cloud RegistrationTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MEDPNet: Achieving High-Precision Adaptive Registration for Complex Die Castings
Due to their complex spatial structure and diverse geometric features, achieving high-precision and robust point cloud registration for complex Die Castings has been a significant challenge in the die-casting industry. E…
Computational EfficiencyPoint Cloud Registration3D Point Cloud Registration with Learning-based Matching Algorithm
We present a novel differential matching algorithm for 3D point cloud registration. Instead of only optimizing the feature extractor for a matching algorithm, we propose a learning-based matching module optimized to the …
Point Cloud RegistrationLPRnet: A self-supervised registration network for LiDAR and photogrammetric point clouds
LiDAR and photogrammetry are active and passive remote sensing techniques for point cloud acquisition, respectively, offering complementary advantages and heterogeneous. Due to the fundamental differences in sensing mech…
Point Cloud RegistrationCross3DReg: Towards a Large-scale Real-world Cross-source Point Cloud Registration Benchmark
Cross-source point cloud registration, which aims to align point cloud data from different sensors, is a fundamental task in 3D vision. However, compared to the same-source point cloud registration, cross-source registra…
Point Cloud RegistrationPoint CloudsMemory-Efficient Point Cloud Registration via Overlapping Region Sampling
Recent advances in deep learning have improved 3D point cloud registration but increased graphics processing unit (GPU) memory usage, often requiring preliminary sampling that reduces accuracy. We propose an overlapping …
GPUPoint Cloud Registration