Deep Point Cloud Normal Estimation via Triplet Learning

• URL: http://arxiv.org/abs/2110.10494v2
• Date: Sat, 23 Mar 2024 14:52:51 GMT
• Title: Deep Point Cloud Normal Estimation via Triplet Learning
• Authors: Weijia Wang, Xuequan Lu, Dasith de Silva Edirimuni, Xiao Liu, Antonio Robles-Kelly,
• Abstract summary: We propose a novel normal estimation method for point clouds. It consists of two phases: (a) feature encoding which learns representations of local patches, and (b) normal estimation that takes the learned representation as input and regresses the normal vector. Our method preserves sharp features and achieves better normal estimation results on CAD-like shapes.
• Score: 12.271669779096076
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Normal estimation on 3D point clouds is a fundamental problem in 3D vision and graphics. Current methods often show limited accuracy in predicting normals at sharp features (e.g., edges and corners) and less robustness to noise. In this paper, we propose a novel normal estimation method for point clouds. It consists of two phases: (a) feature encoding which learns representations of local patches, and (b) normal estimation that takes the learned representation as input and regresses the normal vector. We are motivated that local patches on isotropic and anisotropic surfaces have similar or distinct normals, and that separable features or representations can be learned to facilitate normal estimation. To realise this, we first construct triplets of local patches on 3D point cloud data, and design a triplet network with a triplet loss for feature encoding. We then design a simple network with several MLPs and a loss function to regress the normal vector. Despite having a smaller network size compared to most other methods, experimental results show that our method preserves sharp features and achieves better normal estimation results on CAD-like shapes.

Related papers

• NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Function [55.86697795177619]
  Normal estimation for 3D point clouds is a fundamental task in 3D geometry processing. We introduce a new paradigm for learning neural gradient functions, which encourages the neural network to fit the input point clouds. Our excellent results on widely used benchmarks demonstrate that our method can learn more accurate normals for both unoriented and oriented normal estimation tasks.
  arXiv  Detail & Related papers  (2023-11-01T09:25:29Z)
• Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation [53.19926259132379]
  We propose a novel method called SHS-Net for oriented normal estimation of point clouds by learning signed hyper surfaces. The signed hyper surfaces are implicitly learned in a high-dimensional feature space where the local and global information is aggregated. An attention-weighted normal prediction module is proposed as a decoder, which takes the local and global latent codes as input to predict oriented normals.
  arXiv  Detail & Related papers  (2023-05-10T03:40:25Z)
• Weighted Point Cloud Normal Estimation [16.26518988623745]
  We introduce a weighted normal estimation method for 3D point cloud data. We propose a novel weighted normal regression technique that predicts point-wise weights from local point patches. Our method can robustly handle noisy and complex point clouds, achieving state-of-the-art performance on both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2023-05-06T10:46:56Z)
• NeAF: Learning Neural Angle Fields for Point Normal Estimation [46.58627482563857]
  We propose an implicit function to learn an angle field around the normal of each point in the spherical coordinate system. Instead of directly predicting the normal of an input point, we predict the angle offset between the ground truth normal and a randomly sampled query normal.
  arXiv  Detail & Related papers  (2022-11-30T10:11:47Z)
• Contrastive Learning for Joint Normal Estimation and Point Cloud Filtering [12.602645108896636]
  We propose a novel deep learning method to jointly estimate normals and filter point clouds. We first introduce a 3D patch based contrastive learning framework, with noise corruption as an augmentation. Experimental results show that our method well supports the two tasks simultaneously and preserves sharp features and fine details.
  arXiv  Detail & Related papers  (2022-08-14T09:16:25Z)
• SNAKE: Shape-aware Neural 3D Keypoint Field [62.91169625183118]
  Detecting 3D keypoints from point clouds is important for shape reconstruction. This work investigates the dual question: can shape reconstruction benefit 3D keypoint detection? We propose a novel unsupervised paradigm named SNAKE, which is short for shape-aware neural 3D keypoint field.
  arXiv  Detail & Related papers  (2022-06-03T17:58:43Z)
• Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction [87.08227378010874]
  We show the importance of the high-order 3D geometric constraints for depth prediction. By designing a loss term that enforces a simple geometric constraint, we significantly improve the accuracy and robustness of monocular depth estimation. We show state-of-the-art results of learning metric depth on NYU Depth-V2 and KITTI.
  arXiv  Detail & Related papers  (2021-03-07T00:08:21Z)
• Deep Feature-preserving Normal Estimation for Point Cloud Filtering [14.411519695767634]
  We propose a novel feature-preserving normal estimation method for point cloud filtering. It is a learning method and thus achieves automatic prediction for normals. Various experiments demonstrate that our method outperforms state-of-the-art normal estimation methods and point cloud filtering techniques.
  arXiv  Detail & Related papers  (2020-04-24T07:05:48Z)
• Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild [104.61677518999976]
  We propose Pixel-in-Pixel Net (PIPNet) for facial landmark detection. The proposed model is equipped with a novel detection head based on heatmap regression. To further improve the cross-domain generalization capability of PIPNet, we propose self-training with curriculum.
  arXiv  Detail & Related papers  (2020-03-08T12:23:42Z)

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.