GRE-Diff, a controllable and interactive diffusion-based framework that automates the creation and editing of apartment floor plans under user-specified constraints, is proposed, offering a practical step toward bridging AI-driven automation and human creativity in spatial design.
Abstract
Designing functional and aesthetically coherent floor plans requires exploring a vast space of possible room arrangements, a task that quickly becomes overwhelming for human designers. In this paper, we propose GRE-Diff, a controllable and interactive diffusion-based framework that automates the creation and editing of apartment floor plans under user-specified constraints. By combining AI-generated suggestions with real-time, human-in-the-loop editing, the system enables users to specify room types, room counts, boundary shapes, and editing operations through LLM-parsed instructions or GUI-based interaction. It then generates a diverse set of plausible and well-structured designs for refinement. At the core of our approach is Gaussian Room Embedding (GRE), a continuous latent representation that models each room as a spatial Gaussian distribution capturing its location and extent. Extensive experiments on the RPLAN dataset show that GRE-Diff produces high-quality, constraint-aware, and editable polygonal layouts, offering a practical step toward bridging AI-driven automation and human creativity in spatial design.
The designs produced by Mise-en-Sc\`ene are the closest to the ground truth in perceived quality among all compared methods, by a wide margin over both an LLM layout planner and a specialized layout transformer, while the match-and-place stage bridges the remaining fidelity gap to the ground-truth composites.
Zipeng Xu, Ryan Murdock, Umberto Michieli· 0 citations
Understanding and generating spatially coherent layouts from natural language remains a fundamental yet challenging task for large language models (LLMs). Existing LLMs often struggle to capture explicit geometric relationships and structural dependencies between objects. To address this issue, we propose SG-Layout, a graph-guided layout generation framework that explicitly incorporates structured spatial knowledge into LLMs. SG-Layout follows a two-stage training paradigm: (1) a graph-language feature alignment stage, where a relational graph encoder and a projector are trained to map scene-graph embeddings into the LLM's linguistic space; and (2) an instruction tuning stage, where LoRA-based adapters enable efficient fine-tuning for instruction-driven layout generation while keeping the backbone frozen. We evaluate SG-Layout on image layout generation, indoor scene synthesis and robotic object rearrangement tasks. Experimental results show that SG-Layout improves spatial reasoning accuracy and geometric consistency over the compact open-source backbone, with particularly clear advantages in relation-dense and compositionally complex scenes. These results highlight the effectiveness of graph-structured feature alignment for enhancing controllable layout generation.
Junsheng Wang, Chao Chen, Mengying Xie et al.· 0 citations
Layout understanding, or the interpretation of element organization, is essential for document analysis, user interface (UI) creation, and graphic design. While recent vision-language models (VLMs) excel at interpreting atomic layouts composed of independent elements, they struggle with compositional layouts that require reasoning over visually entangled elements within hierarchical multi-layer structures. In this paper, we introduce a new task, compositional layout understanding, and present CoDeLayout, a VQA dataset of ~20K real-world multi-layer layouts annotated with compositional element pairs and design intent. Through empirical analysis on CoDeLayout, we identify two key challenges for existing VLMs: semantic drift between textual metadata and visual content, and structural ambiguity in hierarchical inter-element relationships. To address these challenges, we propose MASON, a post-training paradigm that integrates multimodal alignment (MA) and structural perception (SP). MA enhances element interpretation by grounding metadata-defined elements to their visual counterparts, mitigating semantic drift, while SP models layer-aware inter-element spatial relationships to improve hierarchical understanding and reduce structural ambiguity. Experiments reveal substantial gaps in existing VLMs: even the strongest baseline, GPT-o3, achieves only 79.68% accuracy, whereas Qwen2.5-VL 7B with MASON reaches 91.66%. Notably, MASON surpasses full-data Direct Finetune using only 30% of the training data and scales better with additional data.
Yiyang Huang, Zhaowen Wang, Simon Jenni et al.· 0 citations
Force-Directed Placement (FDP) is a widely used approach for network visualization, yet scaling it to massive graphs while preserving clear community structures remains a major computational and visual challenge. Existing approximation methods often rely on auxiliary data structures (e.g., spatial trees), which introduce substantial memory overhead; furthermore, traditional power-function-based forces frequently fail to separate dense clusters effectively. In this paper, we present a negative sampling-based algorithm that achieves O(|E|) time complexity with a low memory footprint, without requiring complex multi-level representations. In a first step, we introduce a linearly normalized degree-weighting scheme, which, combined with short-range bounded $t$-distribution forces, effectively untangles dense structures and enhances visual cluster separation. To optimize for this formulation efficiently, we introduce an edge-centric negative sampling strategy that naturally reconstructs the global degree-weighted objective. Furthermore, we design a lock-free, bundle-based parallelization scheme that leverages the sparsity of stochastic updates to achieve significant speedups while mitigating access conflicts. Comprehensive evaluations on 12 large-scale graphs demonstrate that the proposed method outperforms state-of-the-art algorithms in neighborhood preservation and cluster separation. Compared to existing baselines, our method reduces memory consumption by 72% on average and leverages simple GPU parallelism to generate a high-quality layout for a graph with 4 million nodes and 34 million edges in below 10 seconds.
Xin Chen, Shuowei Hou, Yifan Wang et al.· 0 citations
This work presents StructuredEdit, a pipeline that reframes design editing as parameter manipulation rather than pixel generation and embeds hard design constraints into vision-language model fine-tuning by backpropagating pixel-level constraint violations through a lightweight differentiable rasterizer.
This work introduces SON-1K, a comprehensive benchmark for text-to-image generation, and proposes a new approach, the enhanced LMDpp, enhancing the performance of the novel two-stage Large Language Model (LLM)-grounded diffusion model pipeline (LMD).
Weiyue Li, Yi Li, Xiaoyue Wang et al.· 0 citations