SDesc3D: Towards Layout-Aware 3D Indoor Scene Generation from Short Descriptions

TL;DR

SDesc3D introduces a novel framework for generating 3D indoor scenes from short descriptions by leveraging multi-view priors and functionality-based spatial reasoning, improving plausibility and detail.

Contribution

It proposes a multi-view prior augmentation and functionality-aware layout grounding to enhance 3D scene generation from sparse textual inputs.

Findings

Outperforms existing methods on short-text conditioned 3D scene generation

Enables more plausible and detailed 3D indoor scenes

Uses iterative reflection-rectification for structural refinement

Abstract

3D indoor scene generation conditioned on short textual descriptions provides a promising avenue for interactive 3D environment construction without the need for labor-intensive layout specification. Despite recent progress in text-conditioned 3D scene generation, existing works suffer from poor physical plausibility and insufficient detail richness in such semantic condensation cases, largely due to their reliance on explicit semantic cues about compositional objects and their spatial relationships. This limitation highlights the need for enhanced 3D reasoning capabilities, particularly in terms of prior integration and spatial anchoring. Motivated by this, we propose SDesc3D, a short-text conditioned 3D indoor scene generation framework, that leverages multi-view structural priors and regional functionality implications to enable 3D layout reasoning under sparse textual guidance. Specifically, we introduce a Multi-view scene prior augmentation that enriches underspecified textual inputs with aggregated multi-view structural knowledge, shifting from inaccessible semantic relation cues to multi-view relational prior aggregation. Building on this, we design a Functionality-aware layout grounding, employing regional functionality grounding for implicit spatial anchors and conducting hierarchical layout reasoning to enhance scene organization and semantic plausibility. Furthermore, an Iterative reflection-rectification scheme is employed for progressive structural plausibility refinement via self-rectification. Extensive experiments show that our method outperforms existing approaches on short-text conditioned 3D indoor scene generation. Code will be publicly available.