Research map / Point clouds / Point cloud classification
PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes
Ahmed Abdelreheem, Filippo Aleotti, Jamie Watson, Zawar Qureshi, Abdelrahman Eldesokey, Peter Wonka, Gabriel Brostow, Sara Vicente, Guillermo Garcia-Hernando
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 |
|---|---|---|---|
| replace superpoint pooling with uniform spatial pooling (ablation) | Reason3D adaptation · PlaceIt3D benchmark | spatial accuracy: 37.5 -> 47.4 | Improved |
| replace superpoint pooling with uniform spatial pooling (ablation) | Reason3D adaptation · PlaceIt3D benchmark | complete placement success: 13.2 -> 10.1 | Hurt |
| add positional embedding to scene features (ablation) | PlaceWizard variant · PlaceIt3D benchmark | global constraint accuracy: 48.9 -> 50.4 | Improved |
| add PointBert asset encoder instead of text dimensions (ablation) | PlaceWizard variant · PlaceIt3D benchmark | global constraint accuracy: 50.4 -> 49.3 | No clear effect |
| add anchor prediction auxiliary head (ablation) | PlaceWizard variant · PlaceIt3D benchmark | spatial accuracy: 47.1 -> 54.3 | Improved |
| add anchor prediction auxiliary head (ablation) | PlaceWizard variant · PlaceIt3D benchmark | complete placement success: 9.6 -> 12.3 | Improved |
| add anchor prediction auxiliary head (ablation) | PlaceWizard variant · PlaceIt3D benchmark | global constraint accuracy: 49.3 -> 42.5 | Hurt |
| add rotation prediction head (ablation) | PlaceWizard variant · PlaceIt3D benchmark | rotational accuracy: 10.0 -> 14.7 | Improved |
| add asset feature as input to the placement decoder (ablation) | PlaceWizard · PlaceIt3D benchmark | complete placement success: 11.4 -> 15.0 | Improved |
| add asset feature as input to the placement decoder (ablation) | PlaceWizard · PlaceIt3D benchmark | language adherence success: 20.8 -> 25.9 | Improved |
| use full PlaceWizard versus OpenMask3D + rules | PlaceWizard · PlaceIt3D benchmark | global constraint accuracy: 29.2 -> 54.9 | Improved |
| use full PlaceWizard versus OpenMask3D + LLM | PlaceWizard · PlaceIt3D benchmark | complete placement success: 1.6 -> 15.0 | Improved |
Closest papers by meaning
- FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement (CVPR 2025 · similarity 0.90)
- S$^2$-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance (CVPR 2026 · similarity 0.89)
- 3D-PLOT-LLM: Part-Level Object Tokens for 3D Large Language Models (NeurIPS 2026 · similarity 0.89)
- From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes (NeurIPS 2025 · similarity 0.89)
- Let Language Constrain Geometry: Vision–Language Models as Semantic and Spatial Critics for 3D Generation (ICML 2026 · similarity 0.89)
- More Text, Less Point: Towards 3D Data-Efficient Point-Language Understanding (AAAI 2025 · similarity 0.88)
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.
