Research map / Point clouds / Point cloud classification
Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis
Qijian Zhang, Junhui Hou, Yue Qian, Yiming Zeng, Juyong Zhang, Ying He
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 |
|---|---|---|---|
| add CSConv regional embedding (ablation) | FlatNet-Cls-P · ModelNet40 classification | OA (%): 90.5 -> 92.6 | Improved |
| add CSConv regional embedding (ablation) | FlatNet-Cls-D · ModelNet40 classification | OA (%): 92.2 -> 93.4 | Improved |
| use CSConv instead of kxk conv (ablation) | FlatNet-Cls-P · ModelNet40 classification | OA (%): 90.9 -> 92.6 | Improved |
| use CSConv instead of kxk conv (ablation) | FlatNet-Cls-D · ModelNet40 classification | OA (%): 92.5 -> 93.4 | Improved |
| add CSConv regional embedding (ablation) | FlatNet-Seg-P · ShapeNetPart part segmentation | mIoU (%): 84.1 -> 84.9 | Improved |
| add CSConv regional embedding (ablation) | FlatNet-Seg-D · ShapeNetPart part segmentation | mIoU (%): 85.2 -> 85.8 | Improved |
| use CSConv instead of kxk conv (ablation) | FlatNet-Seg-P · ShapeNetPart part segmentation | mIoU (%): 84.5 -> 84.9 | Improved |
| use CSConv instead of kxk conv (ablation) | FlatNet-Seg-D · ShapeNetPart part segmentation | mIoU (%): 85.5 -> 85.8 | Improved |
| replace PointNet-vanilla input with PGI representation | PointNet-vanilla · ModelNet40 classification | OA (%): 87.1 -> 92.6 | Improved |
| replace DGCNN input with PGI representation | DGCNN · ModelNet40 classification | OA (%): 92.9 -> 93.4 | Improved |
| use PGIs instead of equirectangular spherical parameterization | FlatNet-Cls · ModelNet40 classification | OA (%): 88.5 -> 92.6 | Improved |
| use PGIs instead of equirectangular spherical parameterization (stronger variant) | FlatNet-Cls · ModelNet40 classification | OA (%): 90.1 -> 93.4 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 4 on most shared results.
- FPConv — FPConv: Learning Local Flattening for Point Convolution (CVPR 2020) · better on 0 of 1 shared result
- RandLA-Net — RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds (CVPR 2020) · better on 0 of 1 shared result
- SO-Net — SO-Net: Self-Organizing Network for Point Cloud Analysis (CVPR 2018) · better on 0 of 1 shared result
- SpiderCNN — SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters (ECCV 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
- PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling (ECCV 2020 · similarity 0.89)
- GeoNet: Deep Geodesic Networks for Point Cloud Analysis (CVPR 2019 · similarity 0.89)
- Efficient Point Cloud Analysis Using Hilbert Curve (ECCV 2022 · similarity 0.89)
- Flatten Anything: Unsupervised Neural Surface Parameterization (NeurIPS 2024 · similarity 0.88)
- DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization (AAAI 2025 · similarity 0.87)
- LinNet: Linear Network for Efficient Point Cloud Representation Learning (NeurIPS 2024 · similarity 0.87)
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.
