Research map / 3D vision / 3D generation
Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Aggregate multiple scene views through iterative cross-view updates | MulMON · CLE-MV and CLE-Aug | object segmentation mIoU: 0.1891±0.0000 -> 0.7852±0.0008; 0.5137±0.0007 -> 0.7076±0.0004 | Helped |
| Use object-centric multi-view scene representations instead of GQN's single-slot representation | MulMON vs. GQN · CLE-MV and CLE-Aug | predicted observation RMSE: 0.1426±0.0002 -> 0.0464±0.0004; 0.1482±0.0001 -> 0.0733±0.0003 | Helped |
| Use object-centric multi-view scene representations instead of GQN's single-slot representation | MulMON vs. GQN · GQN-Jaco | predicted observation RMSE: 0.1675±0.0013 -> 0.1607±0.0018 | Helped |
| Increase the number of observations used for scene learning (ablation) | MulMON · CLE-MV and CLE-Aug novel-view prediction | prediction performance | Helped |
| Increase object slots until the slot count reaches the maximum number of scene objects (ablation) | MulMON · CLE-MV novel-view prediction | prediction performance: K=7 | Helped |
| Increase object slots beyond the maximum number of scene objects (ablation) | MulMON · CLE-MV novel-view prediction | prediction performance | No clear effect |
| Increase the information-gain coefficient (ablation) | MulMON · Multi-view scene learning | uncertainty reduction rate: 0.1, 1.0, 10.0 and 100.0 | Hurt |
Closest papers by meaning
- Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering (NeurIPS 2026 · similarity 0.88)
- Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection (NeurIPS 2024 · similarity 0.87)
- Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs (AAAI 2026 · similarity 0.87)
- Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction (NeurIPS 2025 · similarity 0.86)
- Multi-Part Object Representations via Graph Structures and Co-Part Discovery (NeurIPS 2026 · similarity 0.86)
- Identifiable Object Representations under Spatial Ambiguities (ICML 2025 · similarity 0.86)
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.