Datasets › Text-to-3D House Model
Text-to-3D House Model (Text--to--3D House Model)
The dataset contains 2,000 houses, 13,478 rooms and 873 (some rooms have same textures so this number is smaller than the total number of rooms.) texture images with corresponding natural language descriptions. These descriptions are firstly generated from some pre-defined templates and then refined by human workers. The average length of the description is 173.73 and there are 193 unique words. In our experiments, we use 1,600 pairs for training while 400 for testing in the building layout generation. For texture synthesis, we use 503 data for training and 370 data for testing.
Benchmarks archive 2025-07-28
No leaderboard in the archive resolves to this dataset.
Papers archive 2025-07-28
No paper in the archive has a leaderboard row on this dataset; the archive counts 3 papers for it but never published that list.
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
No task tagged in the archive.
License archive 2025-07-28
No licence recorded in the archive. Absence here is not a statement about the dataset's terms.
Modalities archive 2025-07-28
No modality tagged.
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- Text-to-3D House Model
1 variant name, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections