Research map / Point clouds / Point cloud classification
Efficient Point Cloud Analysis Using Hilbert Curve
Wanli Chen, Xinge Zhu, Guojin Chen, Bei Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| flatten with Hilbert curve instead of reshape function (ablation) | HilbertNet · ModelNet40 | accuracy: 91.2 -> 94.1 | Improved |
| use Hilbert interpolation instead of bilinear or trilinear interpolation (ablation) | HilbertNet · ModelNet40 | accuracy | Improved |
| use Hilbert pooling instead of regular 2D max pooling (ablation) | HilbertNet · ModelNet40 | accuracy | Improved |
| use Hilbert attention instead of 4x4 sparse 2D convolution (ablation) | HilbertNet · ModelNet40 | accuracy | Improved |
| use Hilbert attention instead of 3D convolution (cost) | Hilbert attention · Module cost (voxel 32^3) | FLOPs: 18.86G -> 0.32G | Improved |
| use Hilbert attention instead of NonLocal attention (memory) | Hilbert attention · Module cost (voxel 32^3) | GPU memory: 4G -> 47.8M | Improved |
| use full-width HilbertNet instead of half-width (M) | HilbertNet · ShapeNetPart | mIoU: 86.4 -> 87.1 | Improved |
| use half-width HilbertNet-M instead of PVCNN | HilbertNet-M · ShapeNetPart | mIoU: 86.0 -> 86.4 | Improved |
| use HilbertNet-L (0.25 x C) instead of 3D-UNet | HilbertNet-L · ShapeNetPart | inference time: 347ms -> 42.1ms | Improved |
| use HilbertNet instead of Point Transformer | HilbertNet · S3DIS Area 5 | mIoU: 70.4 -> 70.9 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PointCNN — PointCNN: Convolution On X-Transformed Points (NeurIPS 2018) · better on 2 of 2 shared results
- SO-Net — SO-Net: Self-Organizing Network for Point Cloud Analysis (CVPR 2018) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis (TPAMI 2023 · similarity 0.89)
- Clustering based Point Cloud Representation Learning for 3D Analysis (ICCV 2023 · similarity 0.88)
- Not All Neighbors Matter: Point Distribution-Aware Pruning for 3D Point Cloud (AAAI 2023 · similarity 0.87)
- Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework (ICLR 2022 · similarity 0.87)
- CurveCloudNet: Processing Point Clouds with 1D Structure (CVPR 2024 · similarity 0.87)
- Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
