PlantoGraphy: Incorporating Iterative Design Process into Generative Artificial Intelligence for Landscape Rendering
Open Access
- 11 May 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Abstract
Landscape renderings are realistic images of landscape sites, allowing stakeholders to perceive better and evaluate design ideas. While recent advances in Generative Artificial Intelligence (GAI (generative artificial intelligence)) enable automated generation of landscape renderings, the End to End (endtoend) methods are not compatible with common design processes, leading to insufficient alignment with design idealizations and limited cohesion of iterative landscape design. Informed by a formative study for comprehending design requirements, we present PlantoGraphy, an iterative design system that allows for interactive configuration of generative artificial intelligence models to accommodate human-centered design practice. A two-stage pipeline is incorporated: first, the concretization module transforms conceptual ideas into concrete scene layouts with a domain-oriented large language model; and second, the illustration module converts scene layouts into realistic landscape renderings with a layout-guided diffusion model Fine-tune (finetune)ed through Low-Rank Adaptation (LoRA) (lora). PlantoGraphy has undergone a series of performance evaluations and user studies, demonstrating its effectiveness in landscape rendering generation and the high recognition of its interactive functionality.Keywords
All Related Versions
Funding Information
- Guangzhou Basic and Applied Basic Research Foundation (2023A03J0142, 2024A04J6462)
This publication has 33 references indexed in Scilit:
- LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image Generation2023
- GLIGEN: Open-Set Grounded Text-to-Image Generation2023
- Interactive Image Synthesis with Panoptic Layout Generation2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Specifying Object Attributes and Relations in Interactive Scene Generation2019
- Image Generation from Scene Graphs2018
- Image retrieval using scene graphs2015
- Image Quality Metrics: PSNR vs. SSIM2010
- Design sketches and sketch design toolsKnowledge-Based Systems, 2005
- The nature of landscape design and design processLandscape and Urban Planning, 1994