From Perception to Evaluation: The Capability Hierarchy and Boundaries of AIGC in Assisting Landscape Design
DOI:
https://doi.org/10.6981/FEM.202612_7(12).0001Keywords:
AIGC, landscape design, capability boundaries, human-AI collaboration, design evaluation.Abstract
Generative Artificial Intelligence (AIGC) is rapidly entering the field of landscape design, yet existing discussions mostly focus on tool introductions, and systematic judgments of its capability hierarchy remain insufficient. Based on a review of existing research, representative algorithmic tools, and design practice materials, this paper proposes a three-layer capability framework of "Perception–Generation–Evaluation," and analyzes the actual capabilities and inherent boundaries of AIGC in landscape design layer by layer. The research shows that: at the perception layer, AI can already identify site elements but cannot understand place meaning; at the generation layer, AI can quickly produce scheme images but cannot guarantee rationality, compliance, or constructability; at the evaluation layer, AI can perform calculations and simulations but cannot undertake weight setting and value judgments. The maturity of the three layers decreases successively; the closer to the core of design, the more powerless AI becomes. Accordingly, this paper argues that the positioning of current AIGC is an assistant for perception and generation, rather than a subject for evaluation and decision-making.
Downloads
References
[1] Parasuraman, R., Sheridan, T. B., & Wickens, C. D. (2000). A model for types and levels of human interaction with automation. IEEE Transactions on Systems, Man, and Cybernetics-Part A, 30(3), 286–297. https://doi.org/10.1109/3468.844354
[2] Chen, L. C., Zhu, Y., Papandreou, G., et al. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 801–818). https://doi.org/10.1007/978-3-030-01234-2_49
[3] Redmon, J., Divvala, S., Girshick, R., et al. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 779–788). https://doi.org/10.1109/CVPR.2016.91
[4] Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. In Proceedings of the Conference on Neural Information Processing Systems (NeurIPS). https://arxiv.org/abs/2006.11239
[5] Zhang, L., Rao, A., & Agrawala, M. (2023). Adding conditional control to text-to-image diffusion models. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/ICCV51070.2023.00376
[6] Doshi-Velez, F., & Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608. https://arxiv.org/abs/1702.08608
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Frontiers in Economics and Management

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.





