Comprehending natural language instructions is a charming property for both 2D and 3D layout synthesis systems. Existing methods implicitly model object joint distributions and express object relations, hindering generation's controllability. We introduce InstructLayout, a novel generative framework that integrates a semantic graph prior and a layout decoder to improve controllability and fidelity for 2D and 3D layout synthesis. The proposed semantic graph prior learns layout appearances and object distributions simultaneously, demonstrating versatility across various downstream tasks in a zero-shot manner. To facilitate the benchmarking for text-driven 2D and 3D scene synthesis, we respectively curate two high-quality datasets of layout-instruction pairs from public Internet resources with large language and multimodal models. Extensive experimental results reveal that the proposed method outperforms existing state-of-the-art approaches by a large margin in both 2D and 3D layout synthesis tasks. Thorough ablation studies confirm the efficacy of crucial design components.
@article{arxiv.2407.07580,
title = {InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis with Semantic Graph Prior},
author = {Chenguo Lin and Yuchen Lin and Panwang Pan and Xuanyang Zhang and Yadong Mu},
journal= {arXiv preprint arXiv:2407.07580},
year = {2025}
}
Comments
Accepted to T-PAMI 2025. This paper is an extension of ICLR 2024 "InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior". arXiv admin note: substantial text overlap with arXiv:2402.04717