InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis with Semantic Graph Prior

TL;DR

InstructLayout is a new generative framework that uses a semantic graph prior to enhance controllability and fidelity in 2D and 3D layout synthesis driven by natural language instructions.

Contribution

It introduces a semantic graph prior integrated with a layout decoder, enabling zero-shot versatility and improved controllability in layout synthesis.

Findings

Outperforms state-of-the-art methods significantly in 2D and 3D tasks.

Demonstrates zero-shot generalization across various layout tasks.

Validates effectiveness through extensive ablation studies.

Abstract

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.