Joint Point Cloud Upsampling and Cleaning with Octree-based CNNs

• URL: http://arxiv.org/abs/2410.17001v1
• Date: Tue, 22 Oct 2024 13:23:05 GMT
• Title: Joint Point Cloud Upsampling and Cleaning with Octree-based CNNs
• Authors: Jihe Li, Bo Pang, Peng-Shuai Wang,
• Abstract summary: We present a simple yet efficient method for jointly upsampling and cleaning point clouds. Our method leverages an off-the-shelf octree-based 3D U-Net (OUNet) with minor modifications, enabling the upsampling and cleaning tasks within a single network. Our network directly processes each input point cloud as a whole instead of processing each point cloud patch as in previous works, which significantly eases the implementation and brings at least 47 times faster inference.
• Score: 12.727392181530229
• License:
• Abstract: Recovering dense and uniformly distributed point clouds from sparse or noisy data remains a significant challenge. Recently, great progress has been made on these tasks, but usually at the cost of increasingly intricate modules or complicated network architectures, leading to long inference time and huge resource consumption. Instead, we embrace simplicity and present a simple yet efficient method for jointly upsampling and cleaning point clouds. Our method leverages an off-the-shelf octree-based 3D U-Net (OUNet) with minor modifications, enabling the upsampling and cleaning tasks within a single network. Our network directly processes each input point cloud as a whole instead of processing each point cloud patch as in previous works, which significantly eases the implementation and brings at least 47 times faster inference. Extensive experiments demonstrate that our method achieves state-of-the-art performances under huge efficiency advantages on a series of benchmarks. We expect our method to serve simple baselines and inspire researchers to rethink the method design on point cloud upsampling and cleaning.

Related papers

• Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mapping [54.38209327518066]
  Learning signed distance functions from point clouds is an important task in 3D computer vision. We propose to learn SDFs via a noise to noise mapping, which does not require any clean point cloud or ground truth supervision. Our novelty lies in the noise to noise mapping which can infer a highly accurate SDF of a single object or scene from its multiple or even single noisy observations.
  arXiv  Detail & Related papers  (2024-07-04T03:35:02Z)
• Arbitrary point cloud upsampling via Dual Back-Projection Network [12.344557879284219]
  We propose a Dual Back-Projection network for point cloud upsampling (DBPnet) A Dual Back-Projection is formulated in an up-down-up manner for point cloud upsampling. Experimental results show that the proposed method achieves the lowest point set matching losses.
  arXiv  Detail & Related papers  (2023-07-18T06:11:09Z)
• GP-PCS: One-shot Feature-Preserving Point Cloud Simplification with Gaussian Processes on Riemannian Manifolds [2.8811433060309763]
  We propose a novel, one-shot point cloud simplification method. It preserves both the salient structural features and the overall shape of a point cloud without any prior surface reconstruction step. We evaluate our method on several benchmark and self-acquired point clouds, compare it to a range of existing methods, demonstrate its application in downstream tasks of registration and surface reconstruction.
  arXiv  Detail & Related papers  (2023-03-27T14:05:34Z)
• 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)
• Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation [79.60988242843437]
  We propose a novel approach that achieves self-supervised and magnification-flexible point clouds upsampling simultaneously. Experimental results demonstrate that our self-supervised learning based scheme achieves competitive or even better performance than supervised learning based state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-18T07:18:25Z)
• Deep Point Cloud Simplification for High-quality Surface Reconstruction [24.29310178063052]
  PCS-Net is dedicated to high-quality surface mesh reconstruction while maintaining geometric fidelity. We propose a novel double-scale resampling module to refine the positions of the sampled points. To further retain important shape features, an adaptive sampling strategy with a novel saliency loss is designed.
  arXiv  Detail & Related papers  (2022-03-17T05:22:25Z)
• GenReg: Deep Generative Method for Fast Point Cloud Registration [18.66568286698704]
  We propose a new data-driven registration algorithm by investigating deep generative neural networks to point cloud registration. The experiments on both ModelNet40 and 7Scene datasets demonstrate that the proposed algorithm achieves state-of-the-art accuracy and efficiency.
  arXiv  Detail & Related papers  (2021-11-23T10:52:09Z)
• Revisiting Point Cloud Simplification: A Learnable Feature Preserving Approach [57.67932970472768]
  Mesh and Point Cloud simplification methods aim to reduce the complexity of 3D models while retaining visual quality and relevant salient features. We propose a fast point cloud simplification method by learning to sample salient points. The proposed method relies on a graph neural network architecture trained to select an arbitrary, user-defined, number of points from the input space and to re-arrange their positions so as to minimize the visual perception error.
  arXiv  Detail & Related papers  (2021-09-30T10:23:55Z)
• 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)
• SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification [93.54286830844134]
  We propose a method for 3D object completion and classification based on point clouds. For the decoder stage, we propose regional convolutions, a novel operator aimed at maximizing the global activation entropy. We evaluate our approach on different 3D tasks such as object completion and classification, achieving state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2020-08-17T14:32:35Z)

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.