CS-Net:Contribution-based Sampling Network for Point Cloud Simplification

• URL: http://arxiv.org/abs/2501.10789v1
• Date: Sat, 18 Jan 2025 14:56:09 GMT
• Title: CS-Net:Contribution-based Sampling Network for Point Cloud Simplification
• Authors: Tian Guo, Chen Chen, Hui Yuan, Xiaolong Mao, Raouf Hamzaoui, Junhui Hou,
• Abstract summary: Point cloud sampling plays a crucial role in reducing computation costs and storage requirements for various vision tasks. Traditional sampling methods, such as farthest point sampling, lack task-specific information. We propose a contribution-based sampling network (CS-Net), where the sampling operation is formulated as a Top-k operation.
• Score: 50.55658910053004
• License:
• Abstract: Point cloud sampling plays a crucial role in reducing computation costs and storage requirements for various vision tasks. Traditional sampling methods, such as farthest point sampling, lack task-specific information and, as a result, cannot guarantee optimal performance in specific applications. Learning-based methods train a network to sample the point cloud for the targeted downstream task. However, they do not guarantee that the sampled points are the most relevant ones. Moreover, they may result in duplicate sampled points, which requires completion of the sampled point cloud through post-processing techniques. To address these limitations, we propose a contribution-based sampling network (CS-Net), where the sampling operation is formulated as a Top-k operation. To ensure that the network can be trained in an end-to-end way using gradient descent algorithms, we use a differentiable approximation to the Top-k operation via entropy regularization of an optimal transport problem. Our network consists of a feature embedding module, a cascade attention module, and a contribution scoring module. The feature embedding module includes a specifically designed spatial pooling layer to reduce parameters while preserving important features. The cascade attention module combines the outputs of three skip connected offset attention layers to emphasize the attractive features and suppress less important ones. The contribution scoring module generates a contribution score for each point and guides the sampling process to prioritize the most important ones. Experiments on the ModelNet40 and PU147 showed that CS-Net achieved state-of-the-art performance in two semantic-based downstream tasks (classification and registration) and two reconstruction-based tasks (compression and surface reconstruction).

Related papers

• Point Cloud Pre-training with Diffusion Models [62.12279263217138]
  We propose a novel pre-training method called Point cloud Diffusion pre-training (PointDif) PointDif achieves substantial improvement across various real-world datasets for diverse downstream tasks such as classification, segmentation and detection.
  arXiv  Detail & Related papers  (2023-11-25T08:10:05Z)
• Parametric Surface Constrained Upsampler Network for Point Cloud [33.033469444588086]
  We introduce a novel surface regularizer into the upsampler network by forcing the neural network to learn the underlying parametric surface represented by bicubic functions and rotation functions. These designs are integrated into two different networks for two tasks that take advantages of upsampling layers. The state-of-the-art experimental results on both tasks demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2023-03-14T21:12:54Z)
• OST: Efficient One-stream Network for 3D Single Object Tracking in Point Clouds [6.661881950861012]
  We propose a novel one-stream network with the strength of the instance-level encoding, which avoids the correlation operations occurring in previous Siamese network. The proposed method has achieved considerable performance not only for class-specific tracking but also for class-agnostic tracking with less computation and higher efficiency.
  arXiv  Detail & Related papers  (2022-10-16T12:31:59Z)
• APSNet: Attention Based Point Cloud Sampling [0.7734726150561088]
  We develop an attention-based point cloud sampling network (APSNet) to tackle this problem. Both supervised learning and knowledge distillation-based self-supervised learning of APSNet are proposed. Experiments demonstrate the superior performance of APSNet against state-of-the-arts in various downstream tasks.
  arXiv  Detail & Related papers  (2022-10-11T17:30:46Z)
• BIMS-PU: Bi-Directional and Multi-Scale Point Cloud Upsampling [60.257912103351394]
  We develop a new point cloud upsampling pipeline called BIMS-PU. We decompose the up/downsampling procedure into several up/downsampling sub-steps by breaking the target sampling factor into smaller factors. We show that our method achieves superior results to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-06-25T13:13:37Z)
• Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point Clouds [46.33828400918886]
  We show how we can train an almost-universal meta-sampler across multiple tasks. This meta-sampler can then be rapidly fine-tuned when applied to different datasets, networks, or even different tasks.
  arXiv  Detail & Related papers  (2022-03-30T02:21:34Z)
• Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling [52.464516118826765]
  We introduce RandLA-Net, an efficient and lightweight neural architecture to infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Our RandLA-Net can process 1 million points in a single pass up to 200x faster than existing approaches.
  arXiv  Detail & Related papers  (2021-07-06T05:08:34Z)
• SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimization [52.20602782690776]
  It is expensive and tedious to obtain large scale paired sparse-canned point sets for training from real scanned sparse data. We propose a self-supervised point cloud upsampling network, named SPU-Net, to capture the inherent upsampling patterns of points lying on the underlying object surface. We conduct various experiments on both synthetic and real-scanned datasets, and the results demonstrate that we achieve comparable performance to the state-of-the-art supervised methods.
  arXiv  Detail & Related papers  (2020-12-08T14:14:09Z)
• 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.