AI Paper Atlas

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

ICCV 2025 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 9 citations (OpenAlex)

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 changedWhereMeasuredEffect
replace superpoint pooling with uniform spatial pooling (ablation)Reason3D adaptation · PlaceIt3D benchmarkspatial accuracy: 37.5 -> 47.4Improved
replace superpoint pooling with uniform spatial pooling (ablation)Reason3D adaptation · PlaceIt3D benchmarkcomplete placement success: 13.2 -> 10.1Hurt
add positional embedding to scene features (ablation)PlaceWizard variant · PlaceIt3D benchmarkglobal constraint accuracy: 48.9 -> 50.4Improved
add PointBert asset encoder instead of text dimensions (ablation)PlaceWizard variant · PlaceIt3D benchmarkglobal constraint accuracy: 50.4 -> 49.3No clear effect
add anchor prediction auxiliary head (ablation)PlaceWizard variant · PlaceIt3D benchmarkspatial accuracy: 47.1 -> 54.3Improved
add anchor prediction auxiliary head (ablation)PlaceWizard variant · PlaceIt3D benchmarkcomplete placement success: 9.6 -> 12.3Improved
add anchor prediction auxiliary head (ablation)PlaceWizard variant · PlaceIt3D benchmarkglobal constraint accuracy: 49.3 -> 42.5Hurt
add rotation prediction head (ablation)PlaceWizard variant · PlaceIt3D benchmarkrotational accuracy: 10.0 -> 14.7Improved
add asset feature as input to the placement decoder (ablation)PlaceWizard · PlaceIt3D benchmarkcomplete placement success: 11.4 -> 15.0Improved
add asset feature as input to the placement decoder (ablation)PlaceWizard · PlaceIt3D benchmarklanguage adherence success: 20.8 -> 25.9Improved
use full PlaceWizard versus OpenMask3D + rulesPlaceWizard · PlaceIt3D benchmarkglobal constraint accuracy: 29.2 -> 54.9Improved
use full PlaceWizard versus OpenMask3D + LLMPlaceWizard · PlaceIt3D benchmarkcomplete placement success: 1.6 -> 15.0Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy