paper-with-me

홈 › Papers

3DRegNet: A Deep Neural Network for 3D Point Registration

2019-04-02 · CVPR 2020 6 · G. Dias Pais, Srikumar Ramalingam, Venu Madhav Govindu, Jacinto C. Nascimento, Rama Chellappa, Pedro Miraldo

We present 3DRegNet, a novel deep learning architecture for the registration of 3D scans. Given a set of 3D point correspondences, we build a deep neural network to address the following two challenges: (i) classification of the point correspondences into inliers/outliers, and (ii) regression of the motion parameters that align the scans into a common reference frame. With regard to regression, we present two alternative approaches: (i) a Deep Neural Network (DNN) registration and (ii) a Procrustes approach using SVD to estimate the transformation. Our correspondence-based approach achieves a higher speedup compared to competing baselines. We further propose the use of a refinement network, which consists of a smaller 3DRegNet as a refinement to improve the accuracy of the registration. Extensive experiments on two challenging datasets demonstrate that we outperform other methods and achieve state-of-the-art results. The code is available.

📄 PDF Abstract BibTeX arXiv:1904.01701

Code (1)

3DVisionISR/3DRegNet 공식 구현 tf

Tasks

regression

Similar Papers 제목 키워드 기반

GMF: General Multimodal Fusion Framework for Correspondence Outlier Rejection

2022-11-01 · Xiaoshui Huang, Wentao Qu, Yifan Zuo, Yuming Fang 외

Rejecting correspondence outliers enables to boost the correspondence quality, which is a critical step in achieving high point cloud registration accuracy. The current state-of-the-art correspondence outlier rejection m…

Point Cloud RegistrationPosition

3D Meta-Registration: Meta-learning 3D Point Cloud Registration Functions

2021-09-29 · Yu Hao, Yi Fang

Learning robust 3D point cloud registration functions with deep neural networks has emerged as a powerful paradigm in recent years, offering promising performance in producing spatial geometric transformations for each p…

Meta-LearningPoint Cloud Registration

SDFReg: Learning Signed Distance Functions for Point Cloud Registration

2023-04-18 · Leida Zhang, Zhengda Lu, Kai Liu, Yiqun Wang

Learning-based point cloud registration methods can handle clean point clouds well, while it is still challenging to generalize to noisy, partial, and density-varying point clouds. To this end, we propose a novel point c…

Point Cloud Registration

3D Meta-Registration: Learning to Learn Registration of 3D Point Clouds

2020-10-22 · Lingjing Wang, Yu Hao, Xiang Li, Yi Fang

Deep learning-based point cloud registration models are often generalized from extensive training over a large volume of data to learn the ability to predict the desired geometric transformation to register 3D point clou…

Meta-LearningPoint Cloud Registration

VRHCF: Cross-Source Point Cloud Registration via Voxel Representation and Hierarchical Correspondence Filtering

2024-03-15 · Guiyu Zhao, Zewen Du, Zhentao Guo, Hongbin Ma

Addressing the challenges posed by the substantial gap in point cloud data collected from diverse sensors, achieving robust cross-source point cloud registration becomes a formidable task. In response, we present a novel…

Point Cloud Registration