Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Text2City: One-Stage Text-Driven Urban Layout Regeneration
Authors: Yiming Qin, Nanxuan Zhao, Bin Sheng, Rynson W.H. Lau
AAAI 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Qualitative and quantitative evaluations show that our proposed method outperforms the baseline methods in regenerating desirable urban layouts that meet the textual descriptions. In this section, we compare our method with state-of-the-art (SOTA) methods both qualitatively and quantitatively. Besides, a user study is conducted to evaluate the performance of our method. Furthermore, we demonstrate the effectiveness of our method through an ablation study. |
| Researcher Affiliation | Collaboration | Yiming Qin1,2, Nanxuan Zhao3*, Bin Sheng1 , Rynson W.H. Lau2 1Shanghai Jiao Tong University 2City University of Hong Kong 3Adobe Research |
| Pseudocode | No | The paper describes methods and processes in narrative text and figures but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | The code and dataset will be available at https://github.com/Little QBerry/Text2City. |
| Open Datasets | Yes | To train our model, we build a large-scale dataset containing urban layouts and layout descriptions, covering 147K regions. The code and dataset will be available at https://github.com/Little QBerry/Text2City. |
| Dataset Splits | No | The paper mentions fine-tuning on a dataset but does not provide specific details on training, validation, or test dataset splits (e.g., percentages or sample counts). |
| Hardware Specification | Yes | On an RTX 2080ti, it takes about one and a half minutes to complete a text-driven urban layout regeneration using our method. |
| Software Dependencies | No | The paper states 'Our method is implemented using Pytorch' but does not provide specific version numbers for PyTorch or other software dependencies. |
| Experiment Setup | Yes | Our method is implemented using Pytorch. We fine-tune the pre-trained CLIP model on our dataset with a batch size of 64 and an initial learning rate of 1e 8. The Adam optimizer is employed with β1 set to 0.9 and β2 set to 0.98. |