Search papers, labs, and topics across Lattice.
This paper introduces SPG-Layout, a text-driven framework that effectively synthesizes 3D indoor scenes in complex non-Manhattan environments by addressing the limitations of existing methods in modeling non-orthogonal spatial relationships. By leveraging statistical priors of object distributions and employing a hierarchical layout strategy that prioritizes large object placement, SPG-Layout significantly reduces geometric violations while enhancing physical fidelity. Experimental results on a newly constructed benchmark of 500 diverse environments show that SPG-Layout outperforms current techniques in both Manhattan and non-Manhattan settings, demonstrating its robustness and versatility.
SPG-Layout achieves a breakthrough in 3D scene synthesis by generating physically plausible layouts in non-Manhattan environments, outperforming existing methods.
Large Language Models (LLMs) have demonstrated remarkable capabilities in 3D indoor synthesis for Manhattan environments. However, existing methods often fail to capture plausible object layout patterns in non-Manhattan settings, primarily because they struggle to model non-orthogonal spatial relationships, leading to high geometric violations and low physical fidelity. To address this challenge, we propose SPG-Layout, a novel text-driven framework designed to generate physically plausible indoor scenes within complex non-Manhattan environments. Specifically, we first utilize statistical priors of object distributions to guide the training process, enhancing environmental understanding and fidelity. Furthermore, mirroring human design workflows, we adopt a hierarchical layout strategy that prioritizes the placement of large objects, thereby substantially minimizing layout violations. By synergizing these components, SPG-Layout achieves a balanced optimization of semantic realism and physical plausibility. To evaluate performance in these complex settings, we constructed a new benchmark comprising 500 diverse non-Manhattan environments. Extensive experiments demonstrate that SPG-Layout consistently and significantly outperforms existing methods across both Manhattan and non-Manhattan environments. The code will be publicly released.
