Research map / Point clouds / Shape and surface completion
Energy-Based Processes for Exchangeable Data
Mengjiao Yang, Bo Dai, Hanjun Dai, Dale Schuurmans
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 |
|---|---|---|---|
| Use EBP instead of l-GAN for generation | ShapeNet Airplane · ShapeNet Airplane | JSD: 3.61 -> 3.92 | Hurt |
| Use EBP instead of PointFlow for generation | ShapeNet Airplane · ShapeNet Airplane | COV-CD: 46.91 -> 49.38 | Improved |
| Use EBP instead of PointFlow for generation | ShapeNet Airplane · ShapeNet Airplane | MMD-CD: 0.217 -> 0.240 | Hurt |
| Use EBP instead of PointFlow for generation | ShapeNet Chair · ShapeNet Chair | JSD: 1.74 -> 1.53 | Improved |
| Use EBP instead of PointFlow for generation | ShapeNet Chair · ShapeNet Chair | MMD-CD: 2.42 -> 2.59 | Hurt |
| Use EBP instead of PointFlow for generation | ShapeNet Chair · ShapeNet Chair | COV-EMD: 46.98 -> 49.84 | Improved |
| Use EBP instead of PointFlow for generation | ShapeNet Car · ShapeNet Car | JSD: 0.87 -> 0.78 | Improved |
| Use EBP instead of PointFlow for generation | ShapeNet Car · ShapeNet Car | COV-CD: 44.03 -> 51.99 | Improved |
| Use EBP instead of PointFlow for generation | ShapeNet Car · ShapeNet Car | MMD-EMD: 5.22 -> 5.24 | Hurt |
| Use EBP for representation learning rather than FoldingNet | ShapeNet-pretrained ModelNet40 features · ModelNet40 | Accuracy: 88.4 -> 88.3 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- FoldingNet — FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation (CVPR 2018) · better on 0 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
- Energy-Based Modelling for Discrete and Mixed Data via Heat Equations on Structured Spaces (NeurIPS 2024 · similarity 0.86)
- Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling (NeurIPS 2025 · similarity 0.85)
- Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences (NeurIPS 2026 · similarity 0.84)
- Free energy Estimation on Any State Space (NeurIPS 2026 · similarity 0.83)
- Joint Learning of Energy-based Models and their Partition Function (ICML 2025 · similarity 0.83)
- Flow Matching Neural Processes (NeurIPS 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.
