Research map / Detection and segmentation / Open-set and few-shot detection
A Simple Approach for Visual Room Rearrangement: 3D Mapping and Semantic Search
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 |
|---|---|---|---|
| Use voxel-based 3D semantic maps and semantic search rather than the strongest prior baseline, CSR | visual room rearrangement · AI2-THOR Rearrangement Challenge 2022 test | %Fixed Strict: 1.90 -> 16.56 | Helped |
| Use voxel-based 3D semantic maps and semantic search rather than the strongest prior baseline, CSR | visual room rearrangement · AI2-THOR Rearrangement Challenge 2022 test | Success: 0.40 -> 4.70 | Helped |
| Add semantic search to the method (ablation) | Ours · AI2-THOR Rearrangement Challenge 2022 test | %Fixed Strict: 15.11 -> 16.56 | Helped |
| Add semantic search to the method (ablation) | Ours · AI2-THOR Rearrangement Challenge 2022 test | Success: 3.60 -> 4.70 | Helped |
| Replace learned semantic search with ground-truth object locations (ablation) | Ours · AI2-THOR Rearrangement Challenge 2022 test | Success: 4.70 -> 6.10 | Helped |
| Replace Mask R-CNN predictions with ground-truth semantic segmentation (ablation) | Ours · AI2-THOR Rearrangement Challenge 2022 test | Success: 4.70 -> 37.55 | Helped |
| Replace semantic search and segmentation with ground truth (ablation) | Ours · AI2-THOR Rearrangement Challenge 2022 test | Success: 4.70 -> 38.33 | Helped |
| Match object instances using pretrained image features instead of average color (ablation) | Ours · AI2-THOR Rearrangement Challenge 2022 test | %Fixed Strict: 16.62 ± 0.89 -> 23.59 ± 1.03 | Helped |
| Increase the number of navigation goals to more than the small-budget range (ablation) | Ours · AI2-THOR Rearrangement Challenge | %Fixed Strict | Mixed |
Closest papers by meaning
- A Category Agnostic Model for Visual Rearrangment (CVPR 2024 · similarity 0.89)
- Task Planning for Object Rearrangement in Multi-Room Environments (AAAI 2024 · similarity 0.89)
- SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent (NeurIPS 2025 · similarity 0.85)
- EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI (CVPR 2024 · similarity 0.85)
- FAVOR: Full-Body AR-Driven Virtual Object Rearrangement Guided by Instruction Text (AAAI 2024 · similarity 0.85)
- EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents (ICML 2025 · similarity 0.85)
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.