Scene Retargeting: Learning Object Placement with Analogical Transfer

2026-09-29

AI Summary

This study addresses the challenge of generalizing functional context generation for sparse, irregular 3D scene layouts by proposing a cluster-level semantic transfer framework. The method achieves analogical reasoning for object placement by stably transferring spatial organization patterns across diverse layouts, flexibly accommodating instance mismatches and adapting to varied floor plans. Furthermore, it enhances generation quality by integrating fundamental feature space distribution optimization with a physics-constrained refinement strategy. Experimental results demonstrate that the proposed approach surpasses existing state-of-the-art models on the 3D-FRONT dataset and effectively supports downstream applications such as real-to-simulation transfer.

Abstract

Interactive simulations of embodied AI or spatial computing applications build on realistic 3D scenes that support daily activities. However, sparse, irregular layout structures impose scene-specific physical constraints, making it hard to define a generalizable framework for generating similar functional context. We formalize Scene Retargeting as stably transferring the semantically coherent spatial organization across layouts, rather than relying on textual descriptions or pairwise relationships. Our cluster-wise transfer flexibly handles mismatched object instances and adapts to distinctive floor plans. We optimize to preserve the rich semantic context of individual clusters by respecting the spatial distribution of foundation features. We can then impose physical constraints to refine wall contacts, pairwise alignment, or clear passageways and openings. Our framework outperforms state-of-the-art methods on layout generation on the 3D-FRONT dataset, and demonstrates downstream applications including real-to-sim transfer, analogical trajectory transfer, and multi-reference composition.

Problem

• Scene Retargeting
• Object Placement
• Layout Generation
• Embodied AI
• Spatial Computing

Innovation

• Scene Retargeting
• Cluster-wise Transfer
• Foundation Features
• Layout Generation
• Analogical Transfer