Research map / Point clouds / Point cloud classification
AdvectiveNet: An Eulerian-Lagrangian Fluidic Reservoir for Point Cloud Processing
Xingzhe He, Helen Lu Cao, Bo Zhu
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 the advection module (ablation) | AdvectiveNet · ShapeNet | mIoU: 85.3% -> 86.2% | Improved |
| Vary the number of temporal integration steps from 0 to 8 (ablation) | AdvectiveNet · ModelNet10 | accuracy: 93.2; 95.2; 95.4; 94.8; 94.7; 95.1; 95.1; 95.2; 95.1 | No clear effect |
| Choose a 16^3 grid instead of an 8^3 or 32^3 grid (ablation) | AdvectiveNet · ModelNet10, 1024 points | accuracy: 94.4 -> 95.4; 95.1 | Improved |
| Choose a 32^3 grid instead of an 8^3 or 16^3 grid (ablation) | AdvectiveNet · ShapeNet, 2048 points | mIoU: 85.4; 86.1 -> 86.2 | Improved |
| Use PIC/FLIP velocity averaging rather than PIC only (ablation) | AdvectiveNet · ModelNet10 | accuracy | Improved |
| Use the full AdvectiveNet approach | ModelNet40 classification · ModelNet40 | accuracy: 92.8 vs. 92.9 | Mixed |
| Use the full AdvectiveNet approach | AdvectiveNet · S3DIS area 5 test | mIoU: 54.37 vs 58.27 | Hurt |
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
- DeepLag: Discovering Deep Lagrangian Dynamics for Intuitive Fluid Prediction (NeurIPS 2024 · similarity 0.87)
- A meshfree exterior calculus for generalizable and data-efficient learning of physics from point clouds (NeurIPS 2026 · similarity 0.84)
- Neural SPH: Improved Neural Modeling of Lagrangian Fluid Dynamics (ICML 2024 · similarity 0.84)
- Lagrangian Flow Networks for Conservation Laws (ICLR 2024 · similarity 0.83)
- Symmetric Basis Convolutions for Learning Lagrangian Fluid Mechanics (ICLR 2024 · similarity 0.83)
- A Pioneering Neural Network Method for Efficient and Robust Fuel Sloshing Simulation in Aircraft (AAAI 2025 · similarity 0.83)
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.
