Research map / Detection and segmentation / 3D detection and driving
EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision
Jiahui Lei, Congyue Deng, Karl Schmeckpeper, Leonidas Guibas, Kostas Daniilidis
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 |
|---|---|---|---|
| Use EFEM instead of Box2Mask | 3D object instance segmentation · RealMugs Wild | AP: 45.1 -> 54.1 | Improved |
| Use EFEM instead of Box2Mask | 3D object instance segmentation · RealMugs Wild | A50: 74.8 -> 82.3 | Improved |
| Use EFEM instead of SoftGroup | 3D object instance segmentation · SynKit Pile | AP: 84.6 -> 60.1 | Hurt |
| Use EFEM instead of Box2Mask | 3D object instance segmentation · SynKit Pile | A50: 94.6 -> 78.9 | Hurt |
| Use EFEM instead of supervised baselines | 3D object instance segmentation · RealChairs R(Pile) | AP: 0.4 -> 34.4 | Improved |
| Add Phase-2 joint iterations (ablation) | EFEM · SynKit Pile | AP: 0.548 -> 0.601 | Improved |
| Add Phase-2 joint iterations (ablation) | EFEM · SynKit Pile | AP50: 0.740 -> 0.789 | Improved |
| Add normal error terms (ablation) | EFEM · SynKit Pile | AP: 0.203 -> 0.601 | Improved |
| Add normal error terms (ablation) | EFEM · SynKit Pile | AP50: 0.302 -> 0.789 | Improved |
Later papers that compared with this method
3 later accepted papers report EFEM as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision (CVPR 2026 · better on 2 of 2 shared results)
- FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation (ICML 2026 · better on 1 of 1 shared result)
- GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene Supervision (ICLR 2025 · 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
- Grounding Continuous Representations in Geometry: Equivariant Neural Fields (ICLR 2025 · similarity 0.86)
- Equivariant Neural Rendering (ICML 2020 · similarity 0.86)
- Augmented Equivariant Mesh Networks for Anatomical Segmentation (NeurIPS 2026 · similarity 0.84)
- The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products (ICML 2025 · similarity 0.84)
- Learning Generalizable Shape Completion with SIM(3) Equivariance (NeurIPS 2025 · similarity 0.84)
- Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes (ICML 2025 · similarity 0.84)
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.
