Research map / Detection and segmentation / Open-set and few-shot detection
Unsupervised Object-Based Transition Models For 3D Partially Observable Environments
Antonia Creswell, Rishabh Kabra, Christopher P. Burgess, Murray Shanahan
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 |
|---|---|---|---|
| remove AlignNet (OT vs OAT) (ablation) | OAT · 3D Room | Unroll ARI: 0.42 -> 0.12 | Hurt |
| remove AlignNet (ablation) | OAT · 3D Room | Encoding ARI: 0.62 -> 0.59 | Hurt |
| remove AlignNet (ablation) | OAT · 3D Room | Unroll Pixel Error: 0.0121 -> 0.0143 | Hurt |
| OAT versus OP3 baseline | OAT · 3D Room | Unroll ARI: 0.33 -> 0.42 | Improved |
| OAT versus OP3 baseline | OAT · 3D Room | Encoding ARI: 0.32 -> 0.62 | Improved |
| OAT versus OP3 baseline | OAT · 3D Room | Unroll Pixel Error: 0.0132 -> 0.0121 | Improved |
| use pixel-level loss instead of object-level loss with aligned inputs (ablation) | slot-wise transition model · Ground-truth mask ablation | object-level error: 0.0982 -> 1.04 | Hurt |
| use unaligned inputs with object-level loss (ablation) | slot-wise transition model · Ground-truth mask ablation | object-level error: 0.0982 -> 19.9 | Hurt |
| use unaligned inputs with pixel-level loss (ablation) | slot-wise transition model · Ground-truth mask ablation | object-level error: 1.04 -> 229 | Hurt |
| transformer followed by slot-wise LSTM versus Transformer XL, LSTM, Deep LSTM, recurrent transformer (ablation) | transition core · Ground-truth mask ablation | object and pixel error | Improved |
| lower transition loss weight zeta from 10 to 1.0 (ablation) | OAT · 3D Room | performance: 10 -> 1.0 | No clear effect |
| mask KL weight gamma 0.5 instead of 0.05 (ablation) | OAT MONet · 3D Room | qualitative quality: 0.05 -> 0.5 | No clear effect |
Closest papers by meaning
- Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments (CVPR 2024 · similarity 0.87)
- ObjectMover: Generative Object Movement with Video Prior (CVPR 2025 · similarity 0.86)
- Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations (NeurIPS 2025 · similarity 0.86)
- MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes (CVPR 2025 · similarity 0.86)
- M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation (CVPR 2025 · similarity 0.86)
- Temporally Consistent Object-Centric Learning by Contrasting Slots (CVPR 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.
