Research map / Point clouds / Point cloud classification
Differentiable Convolution Search for Point Cloud Processing
Xing Nie, Yongcheng Liu, Shaohong Chen, Jianlong Chang, Chunlei Huo, Gaofeng Meng, Qi Tian, Weiming Hu, Chunhong Pan
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 epsilon-greedy algorithm to convolution search (ablation) | PointSeaNet · ModelNet40 classification | overall accuracy: 94.0 -> 94.2 | Improved |
| add epsilon-greedy algorithm (ablation) | PointSeaNet · ModelNet40 shape retrieval | mAP: 89.9 -> 90.3 | Improved |
| add epsilon-greedy algorithm (ablation) | PointSeaNet · S3DIS Area-5 | mIoU: 68.2 -> 69.0 | Improved |
| add epsilon-greedy algorithm (ablation) | PointSeaNet · S3DIS 6-fold | mIoU: 71.2 -> 71.9 | Improved |
| add epsilon-greedy algorithm (ablation) | PointSeaNet · ShapeNetPart | class mIoU: 85.2 -> 85.7 | Improved |
| add epsilon-greedy algorithm (ablation) | PointSeaNet · ModelNet40 normal estimation | error: 0.12 -> 0.10 | Improved |
| add local features e2 to e1 (ablation) | PointSeaNet association search · ModelNet40 classification | overall accuracy: 81.3 -> 87.1 | Improved |
| add geometric relations e3 (ablation) | PointSeaNet association search · ModelNet40 classification | overall accuracy: 87.1 -> 90.2 | Improved |
| add Euclidean distance e4 (ablation) | PointSeaNet association search · ModelNet40 classification | overall accuracy: 90.2 -> 92.9 | Improved |
| add salient information e5 (ablation) | PointSeaNet association search · ModelNet40 classification | overall accuracy: 92.9 -> 94.0 | Improved |
| increase cells from 3 to 6 (ablation) | PointSeaNet · ModelNet40 classification | overall accuracy: 93.7 -> 94.2 | Improved |
| increase cells from 6 to 9 (ablation) | PointSeaNet · ModelNet40 classification | overall accuracy: 94.2 -> 94.1 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PointCNN — PointCNN: Convolution On X-Transformed Points (NeurIPS 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
- PointConv: Deep Convolutional Networks on 3D Point Clouds (CVPR 2019 · similarity 0.89)
- Shape-Oriented Convolution Neural Network for Point Cloud Analysis (AAAI 2020 · similarity 0.89)
- RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning (IJCV 2022 · similarity 0.88)
- PointCNN: Convolution On X-Transformed Points (NeurIPS 2018 · similarity 0.88)
- DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis (CVPR 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.
