Research map / Point clouds / Point cloud classification
Interpolated Convolutional Networks for 3D Point Cloud Understanding
Jiageng Mao, Xiaogang Wang, Hongsheng Li
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 |
|---|---|---|---|
| replace 3x3x3 InterpConv by 1x1x1 kernels (PointNet-like) (ablation) | InterpCNN · ModelNet40 | overall accuracy: 89.9% -> 93.0% | Improved |
| use 5x5x5 kernel in first module instead of 3x3x3 (ablation) | InterpCNN · ModelNet40 | overall accuracy: 93.0% -> 92.8% | No clear effect |
| use 5x5x5 kernel in second module instead of 3x3x3 (ablation) | InterpCNN · ModelNet40 | overall accuracy: 93.0% -> 92.9% | No clear effect |
| use smaller kernel lengths (0.05-0.1-0.2 / 0.1-0.2-0.4) (ablation) | InterpCNN · ModelNet40 | overall accuracy: 93.0% -> 92.4% | Hurt |
| use larger kernel lengths (0.2-0.4-0.8 / 0.4-0.8-1.6) (ablation) | InterpCNN · ModelNet40 | overall accuracy: 93.0% -> 91.9% | Hurt |
| use trilinear instead of Gaussian interpolation (ablation) | InterpCNN · ModelNet40 | overall accuracy: 93.0% -> 92.5% | Hurt |
| use trilinear instead of Gaussian interpolation (ablation) | InterpCNN · ShapeNet Parts | instance mIoU: 85.0% -> 86.3% | Improved |
| normalize by sum of interpolation weights instead of number of points (ablation) | InterpCNN · ModelNet40 | overall accuracy: 93.0% -> 92.8% | No clear effect |
| use InterpCNN instead of DGCNN | InterpCNN · ModelNet40 | inference time: 89.7ms -> 31.4ms | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- PointCNN — PointCNN: Convolution On X-Transformed Points (NeurIPS 2018) · better on 4 of 5 shared results
- PointConv — PointConv: Deep Convolutional Networks on 3D Point Clouds (CVPR 2019) · better on 2 of 2 shared results
- SGPN — SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation (CVPR 2018) · better on 1 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
- Shape-Oriented Convolution Neural Network for Point Cloud Analysis (AAAI 2020 · similarity 0.89)
- FPConv: Learning Local Flattening for Point Convolution (CVPR 2020 · similarity 0.89)
- RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning (IJCV 2022 · similarity 0.89)
- PointConv: Deep Convolutional Networks on 3D Point Clouds (CVPR 2019 · similarity 0.89)
- Fully-Convolutional Point Networks for Large-Scale Point Clouds (ECCV 2018 · similarity 0.88)
- 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.
