PointCNN++: Performant Convolution on Native Points

• URL: http://arxiv.org/abs/2511.23227v2
• Date: Tue, 02 Dec 2025 00:45:32 GMT
• Title: PointCNN++: Performant Convolution on Native Points
• Authors: Lihan Li, Haofeng Zhong, Rui Bu, Mingchao Sun, Wenzheng Chen, Baoquan Chen, Yangyan Li,
• Abstract summary: Existing convolutional learning methods for 3D point cloud data are divided into two paradigms.<n> point-based methods preserve geometric precision but often face performance challenges.<n>voxel-based methods achieve high efficiency through quantization at the cost of geometric fidelity.<n>We propose PointCNN++, a novel architectural design that fundamentally mitigates this precision-performance trade-off.
• Score: 25.82514121801553
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing convolutional learning methods for 3D point cloud data are divided into two paradigms: point-based methods that preserve geometric precision but often face performance challenges, and voxel-based methods that achieve high efficiency through quantization at the cost of geometric fidelity. This loss of precision is a critical bottleneck for tasks such as point cloud registration. We propose PointCNN++, a novel architectural design that fundamentally mitigates this precision-performance trade-off. It $\textbf{generalizes sparse convolution from voxels to points}$, treating voxel-based convolution as a specialized, degraded case of our more general point-based convolution. First, we introduce a point-centric convolution where the receptive field is centered on the original, high-precision point coordinates. Second, to make this high-fidelity operation performant, we design a computational strategy that operates $\textbf{natively}$ on points. We formulate the convolution on native points as a Matrix-Vector Multiplication and Reduction (MVMR) problem, for which we develop a dedicated, highly-optimized GPU kernel. Experiments demonstrate that PointCNN++ $\textbf{uses an order of magnitude less memory and is several times faster}$ than representative point-based methods. Furthermore, when used as a simple replacement for the voxel-based backbones it generalizes, it $\textbf{significantly improves point cloud registration accuracies while proving both more memory-efficient and faster}$. PointCNN++ shows that preserving geometric detail and achieving high performance are not mutually exclusive, paving the way for a new class of 3D learning with high fidelity and efficiency. Our code will be open sourced.

Related papers

• LitePT: Lighter Yet Stronger Point Transformer [50.6430530112838]
  We analyse the role of different computational blocks in 3D point cloud networks.<n>We propose a new, improved 3D point cloud backbone that employs convolutions in early stages and switches to attention for deeper layers.<n>The resulting LitePT model has $3.6times$ fewer parameters, runs $2times$ faster, and uses $2times$ less memory than the state-of-the-art Point Transformer V3.
  arXiv  Detail & Related papers  (2025-12-15T18:59:57Z)
• Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinement [19.575833741231953]
  We use the KNN method to determine the neighborhoods of raw surface points.<n>A conditional probability model is adaptive to local geometry, leading to significant rate reduction.<n>We incorporate an implicit neural representation into the refinement layer, allowing the decoder to sample points on the underlying surface at arbitrary densities.
  arXiv  Detail & Related papers  (2024-08-06T05:24:06Z)
• Quadric Representations for LiDAR Odometry, Mapping and Localization [93.24140840537912]
  Current LiDAR odometry, mapping and localization methods leverage point-wise representations of 3D scenes. We propose a novel method of describing scenes using quadric surfaces, which are far more compact representations of 3D objects. Our method maintains low latency and memory utility while achieving competitive, and even superior, accuracy.
  arXiv  Detail & Related papers  (2023-04-27T13:52:01Z)
• Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation [66.6890991207065]
  Sparse 3D convolutions have become the de-facto tools to construct deep neural networks. We propose an alternative method that reaches the level of state-of-the-art methods without requiring sparse convolutions. We show that such level of performance is achievable by relying on tools a priori unfit for large scale and high-performing 3D perception.
  arXiv  Detail & Related papers  (2023-01-24T16:10:08Z)
• Stratified Transformer for 3D Point Cloud Segmentation [89.9698499437732]
  Stratified Transformer is able to capture long-range contexts and demonstrates strong generalization ability and high performance. To combat the challenges posed by irregular point arrangements, we propose first-layer point embedding to aggregate local information. Experiments demonstrate the effectiveness and superiority of our method on S3DIS, ScanNetv2 and ShapeNetPart datasets.
  arXiv  Detail & Related papers  (2022-03-28T05:35:16Z)
• Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework [55.40001810884942]
  We introduce a pure residual network, called PointMLP, which integrates no sophisticated local geometrical extractors but still performs very competitively. On the real-world ScanObjectNN dataset, our method even surpasses the prior best method by 3.3% accuracy. Compared to most recent CurveNet, PointMLP trains 2x faster, tests 7x faster, and is more accurate on ModelNet40 benchmark.
  arXiv  Detail & Related papers  (2022-02-15T01:39:07Z)
• Winograd Convolution for Deep Neural Networks: Efficient Point Selection [0.8043754868448141]
  We propose a novel approach to point selection using points of the form -1/c, -c, c, 1/c using the full range of real-valued numbers for c. We find that the error for different values of c forms a rough curve across the range of real-value numbers helping to localize the values of c that reduce error. We study a range of sizes for small convolutions and achieve reduction in error ranging from 2% to around 59% for both 1D and 2D convolutions.
  arXiv  Detail & Related papers  (2022-01-25T15:00:54Z)
• 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)
• Dynamic Convolution for 3D Point Cloud Instance Segmentation [146.7971476424351]
  We propose an approach to instance segmentation from 3D point clouds based on dynamic convolution. We gather homogeneous points that have identical semantic categories and close votes for the geometric centroids. The proposed approach is proposal-free, and instead exploits a convolution process that adapts to the spatial and semantic characteristics of each instance.
  arXiv  Detail & Related papers  (2021-07-18T09:05:16Z)
• Robust Kernel-based Feature Representation for 3D Point Cloud Analysis via Circular Graph Convolutional Network [2.42919716430661]
  We present a new local feature description method that is robust to rotation, density, and scale variations. To improve representations of the local descriptors, we propose a global aggregation method. Our method shows superior performances when compared to the state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-12-22T18:02:57Z)
• DV-ConvNet: Fully Convolutional Deep Learning on Point Clouds with Dynamic Voxelization and 3D Group Convolution [0.7340017786387767]
  3D point cloud interpretation is a challenging task due to the randomness and sparsity of the component points. In this work, we draw attention back to the standard 3D convolutions towards an efficient 3D point cloud interpretation. Our network is able to run and converge at a considerably fast speed, while yields on-par or even better performance compared with the state-of-the-art methods on several benchmark datasets.
  arXiv  Detail & Related papers  (2020-09-07T07:45:05Z)

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.