Representation Learning of Point Cloud Upsampling in Global and Local Inputs

• URL: http://arxiv.org/abs/2501.07076v3
• Date: Thu, 19 Jun 2025 05:03:27 GMT
• Title: Representation Learning of Point Cloud Upsampling in Global and Local Inputs
• Abstract summary: We propose a novel framework, ReLPU, which enhances upsampling performance by explicitly learning from both global and local structural features of point clouds.<n>Our framework was applied to several state-of-the-art autoencoder-based networks and validated on standard datasets.
• Score: 1.4045865137356779
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, point cloud upsampling has been widely applied in tasks such as 3D reconstruction and object recognition. This study proposed a novel framework, ReLPU, which enhances upsampling performance by explicitly learning from both global and local structural features of point clouds. Specifically, we extracted global features from uniformly segmented inputs (Average Segments) and local features from patch-based inputs of the same point cloud. These two types of features were processed through parallel autoencoders, fused, and then fed into a shared decoder for upsampling. This dual-input design improved feature completeness and cross-scale consistency, especially in sparse and noisy regions. Our framework was applied to several state-of-the-art autoencoder-based networks and validated on standard datasets. Experimental results demonstrated consistent improvements in geometric fidelity and robustness. In addition, saliency maps confirmed that parallel global-local learning significantly enhanced the interpretability and performance of point cloud upsampling.

Related papers

• PUFM++: Point Cloud Upsampling via Enhanced Flow Matching [15.738247394527024]
  PUFM++ is an enhanced flow-matching framework for reconstructing point clouds from sparse, noisy, and partial observations.<n>We introduce a two-stage flow-matching strategy that first learns a direct, straight-path flow from sparse inputs to dense targets, and then refines it using noise-perturbed samples to approximate the terminal marginal distribution better.<n>Experiments on synthetic benchmarks and real-world scans show that PUFM++ sets a new state of the art in point cloud upsampling.
  arXiv  Detail & Related papers  (2025-12-24T06:30:42Z)
• PVINet: Point-Voxel Interlaced Network for Point Cloud Compression [83.74785652597248]
  In point cloud compression, the quality of a reconstructed point cloud relies on both the global structure and the local context.<n>We propose a point-voxel interlaced network (PVINet), which captures global structural features and local contextual features in parallel.<n>PVINet delivers competitive performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-09-01T03:37:32Z)
• Asynchronous Feedback Network for Perceptual Point Cloud Quality Assessment [18.65004981045047]
  We propose a novel asynchronous feedback quality prediction network (AFQ-Net)<n>Motivated by human visual perception mechanisms, AFQ-Net employs a dual-branch structure to deal with global and local features.<n>We conduct comprehensive experiments on three datasets and achieve superior performance over the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-07-13T08:52:44Z)
• Mesh Denoising Transformer [104.5404564075393]
  Mesh denoising is aimed at removing noise from input meshes while preserving their feature structures. SurfaceFormer is a pioneering Transformer-based mesh denoising framework. New representation known as Local Surface Descriptor captures local geometric intricacies. Denoising Transformer module receives the multimodal information and achieves efficient global feature aggregation.
  arXiv  Detail & Related papers  (2024-05-10T15:27:43Z)
• Mitigating Prior Shape Bias in Point Clouds via Differentiable Center Learning [19.986150101882217]
  We introduce a novel solution called the Differentiable Center Sampling Network (DCS-Net) It tackles the information leakage problem by incorporating both global feature reconstruction and local feature reconstruction as non-trivial proxy tasks. Experimental results demonstrate that our method enhances the expressive capacity of existing point cloud models.
  arXiv  Detail & Related papers  (2024-02-03T08:58:23Z)
• InvariantOODG: Learning Invariant Features of Point Clouds for Out-of-Distribution Generalization [17.96808017359983]
  We propose InvariantOODG, which learns invariability between point clouds with different distributions. We define a set of learnable anchor points that locate the most useful local regions and two types of transformations to augment the input point clouds. The experimental results demonstrate the effectiveness of the proposed model on 3D domain generalization benchmarks.
  arXiv  Detail & Related papers  (2024-01-08T09:41:22Z)
• Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling [55.05706827963042]
  Point cloud upsampling aims to generate dense and uniformly distributed point sets from a sparse point cloud. Previous methods typically split a sparse point cloud into several local patches, upsample patch points, and merge all upsampled patches. We propose a novel approach that learns an unsigned distance field guided by local priors for point cloud upsampling.
  arXiv  Detail & Related papers  (2023-12-23T01:52:14Z)
• Bidirectional Knowledge Reconfiguration for Lightweight Point Cloud Analysis [74.00441177577295]
  Point cloud analysis faces computational system overhead, limiting its application on mobile or edge devices. This paper explores feature distillation for lightweight point cloud models. We propose bidirectional knowledge reconfiguration to distill informative contextual knowledge from the teacher to the student.
  arXiv  Detail & Related papers  (2023-10-08T11:32:50Z)
• 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)
• OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration [31.108056345511976]
  OMNet is a global feature based iterative network for partial-to-partial point cloud registration. We learn masks in a coarse-to-fine manner to reject non-overlapping regions, which converting the partial-to-partial registration to the registration of the same shapes.
  arXiv  Detail & Related papers  (2021-03-01T11:59:59Z)
• 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)
• Cascaded Refinement Network for Point Cloud Completion with Self-supervision [74.80746431691938]
  We introduce a two-branch network for shape completion. The first branch is a cascaded shape completion sub-network to synthesize complete objects. The second branch is an auto-encoder to reconstruct the original partial input.
  arXiv  Detail & Related papers  (2020-10-17T04:56:22Z)
• Self-Sampling for Neural Point Cloud Consolidation [83.31236364265403]
  We introduce a novel technique for neural point cloud consolidation which learns from only the input point cloud. We repeatedly self-sample the input point cloud with global subsets that are used to train a deep neural network. We demonstrate the ability to consolidate point sets from a variety of shapes, while eliminating outliers and noise.
  arXiv  Detail & Related papers  (2020-08-14T17:16:02Z)
• A Rotation-Invariant Framework for Deep Point Cloud Analysis [132.91915346157018]
  We introduce a new low-level purely rotation-invariant representation to replace common 3D Cartesian coordinates as the network inputs. Also, we present a network architecture to embed these representations into features, encoding local relations between points and their neighbors, and the global shape structure. We evaluate our method on multiple point cloud analysis tasks, including shape classification, part segmentation, and shape retrieval.
  arXiv  Detail & Related papers  (2020-03-16T14:04:45Z)
• An Explicit Local and Global Representation Disentanglement Framework with Applications in Deep Clustering and Unsupervised Object Detection [9.609936822226633]
  We propose a framework, called SPLIT, which allows us to disentangle local and global information. Our framework adds generative assumption to the variational autoencoder (VAE) framework. We show that the framework can effectively disentangle local and global information within these models.
  arXiv  Detail & Related papers  (2020-01-24T12:09:20Z)

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.