AI Paper Atlas

Research map / 3D vision / 3D generation

R$^3$L: Reasoning 3D Layouts from Relative Spatial Relations

Zhifeng Gu, Yuqi Wang, Bing WANG

ICML 2026 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 0 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
add invariant spatial decomposition and consistent spatial imagination (ablation)R3L relation inference · Ablation (physical losses disabled)instruction following: 7.8 -> 9.1Improved
add invariant spatial decomposition (versus imagination only) (ablation)R3L · Ablation (physical losses disabled)instruction following: 8.5 -> 9.1Improved
add consistent spatial imagination (versus decomposition only) (ablation)R3L · Ablation (physical losses disabled)out-of-bound ratio %OR: 6.3 -> 1.6Improved
add consistent spatial imagination (versus decomposition only) (ablation)R3L · Ablation (physical losses disabled)collision ratio %CR: 3.1 -> 1.0Improved
semantic grouping instead of invariant spatial decomposition (ablation)R3L · Ablation (physical losses disabled)realism: 8.0 -> 5.3Hurt
use R3L instead of LayoutGPT3D layout generation · 9 scene types averagecollision and out-of-bound ratios: 4.3% and 8.1% -> 0.0% and 0.0%Improved
add global-to-local pose re-parameterization to optimization (ablation)supportive spatial optimization · Optimization convergenceconvergence speed: 1.8x speedupImproved
add decomposition to reduce reference-frame transformations (ablation)R3L · Placement error by hop countplacement error rateImproved
use R3L instead of Holodeck3D layout generation · 9 scene types averageinstruction following: 3.0 -> 9.1Improved
use R3L instead of LayoutVLM3D layout generation · 9 scene types averagerealism: 4.9 -> 7.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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