Deep-3DAligner: Unsupervised 3D Point Set Registration Network With Optimizable Latent Vector

• URL: http://arxiv.org/abs/2010.00321v1
• Date: Tue, 29 Sep 2020 22:44:38 GMT
• Title: Deep-3DAligner: Unsupervised 3D Point Set Registration Network With Optimizable Latent Vector
• Authors: Lingjing Wang, Xiang Li, Yi Fang
• Abstract summary: We propose to develop a novel model that integrates the optimization to learning, aiming to address the technical challenges in 3D registration. In addition to the deep transformation decoding network, our framework introduce an optimizable deep underlineSpatial underlineCorrelation underlineRepresentation.
• Score: 15.900382629390297
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Point cloud registration is the process of aligning a pair of point sets via searching for a geometric transformation. Unlike classical optimization-based methods, recent learning-based methods leverage the power of deep learning for registering a pair of point sets. In this paper, we propose to develop a novel model that organically integrates the optimization to learning, aiming to address the technical challenges in 3D registration. More specifically, in addition to the deep transformation decoding network, our framework introduce an optimizable deep \underline{S}patial \underline{C}orrelation \underline{R}epresentation (SCR) feature. The SCR feature and weights of the transformation decoder network are jointly updated towards the minimization of an unsupervised alignment loss. We further propose an adaptive Chamfer loss for aligning partial shapes. To verify the performance of our proposed method, we conducted extensive experiments on the ModelNet40 dataset. The results demonstrate that our method achieves significantly better performance than the previous state-of-the-art approaches in the full/partial point set registration task.

Related papers

• Hierarchical Attention and Graph Neural Networks: Toward Drift-Free Pose Estimation [1.745925556687899]
  The most commonly used method for addressing 3D geometric registration is the iterative closet-point algorithm. We propose a framework that replaces traditional geometric registration and pose graph optimization with a learned model utilizing hierarchical attention mechanisms and graph neural networks.
  arXiv  Detail & Related papers  (2023-09-18T16:51:56Z)
• Large-scale Point Cloud Registration Based on Graph Matching Optimization [30.92028761652611]
  We propose a underlineGraph underlineMatching underlineOptimization based underlineNetwork. The proposed method has been evaluated on the 3DMatch/3DLoMatch benchmarks and the KITTI benchmark.
  arXiv  Detail & Related papers  (2023-02-12T03:29:35Z)
• CpT: Convolutional Point Transformer for 3D Point Cloud Processing [10.389972581905]
  We present CpT: Convolutional point Transformer - a novel deep learning architecture for dealing with the unstructured nature of 3D point cloud data. CpT is an improvement over existing attention-based Convolutions Neural Networks as well as previous 3D point cloud processing transformers. Our model can serve as an effective backbone for various point cloud processing tasks when compared to the existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-11-21T17:45:55Z)
• DFC: Deep Feature Consistency for Robust Point Cloud Registration [0.4724825031148411]
  We present a novel learning-based alignment network for complex alignment scenes. We validate our approach on the 3DMatch dataset and the KITTI odometry dataset.
  arXiv  Detail & Related papers  (2021-11-15T08:27:21Z)
• Riggable 3D Face Reconstruction via In-Network Optimization [58.016067611038046]
  This paper presents a method for riggable 3D face reconstruction from monocular images. It jointly estimates a personalized face rig and per-image parameters including expressions, poses, and illuminations. Experiments demonstrate that our method achieves SOTA reconstruction accuracy, reasonable robustness and generalization ability.
  arXiv  Detail & Related papers  (2021-04-08T03:53:20Z)
• FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimation [87.74617110803189]
  Estimating the 3D motion of points in a scene, known as scene flow, is a core problem in computer vision. We present a recurrent architecture that learns a single step of an unrolled iterative alignment procedure for refining scene flow predictions.
  arXiv  Detail & Related papers  (2020-11-19T23:23:48Z)
• Deep Shells: Unsupervised Shape Correspondence with Optimal Transport [52.646396621449]
  We propose a novel unsupervised learning approach to 3D shape correspondence. We show that the proposed method significantly improves over the state-of-the-art on multiple datasets.
  arXiv  Detail & Related papers  (2020-10-28T22:24:07Z)
• Unsupervised Learning of 3D Point Set Registration [15.900382629390297]
  Point cloud registration is the process of aligning a pair of point sets via searching for a geometric transformation. This paper proposes Deep-3DAligner, a novel unsupervised registration framework based on a newly introduced deep Spatial Correlation Representation (SCR) feature. Our method starts with optimizing a randomly latent SCR feature, which is then decoded to a geometric transformation to align source and target point sets.
  arXiv  Detail & Related papers  (2020-06-11T05:21:38Z)
• Learning 3D-3D Correspondences for One-shot Partial-to-partial Registration [66.41922513553367]
  We show that learning-based partial-to-partial registration can be achieved in a one-shot manner. We propose an Optimal Transport layer able to account for occluded points thanks to the use of bins. The resulting OPRNet framework outperforms the state of the art on standard benchmarks.
  arXiv  Detail & Related papers  (2020-06-08T12:35:47Z)
• Joint Multi-Dimension Pruning via Numerical Gradient Update [120.59697866489668]
  We present joint multi-dimension pruning (abbreviated as JointPruning), an effective method of pruning a network on three crucial aspects: spatial, depth and channel simultaneously. We show that our method is optimized collaboratively across the three dimensions in a single end-to-end training and it is more efficient than the previous exhaustive methods.
  arXiv  Detail & Related papers  (2020-05-18T17:57:09Z)
• MOPS-Net: A Matrix Optimization-driven Network forTask-Oriented 3D Point Cloud Downsampling [86.42733428762513]
  MOPS-Net is a novel interpretable deep learning-based method for matrix optimization. We show that MOPS-Net can achieve favorable performance against state-of-the-art deep learning-based methods over various tasks.
  arXiv  Detail & Related papers  (2020-05-01T14:01:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.