Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Official implementation of the paper Plan2Scene.
| Date | Stars |
|---|---|
| 2026-07-24 | 606 |
| 2026-07-25 | 606 |
| 2026-07-28 | 606 |
| 2026-07-30 | 606 |
| 2026-08-06 | 606 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Plan2Scene
Official repository of the paper:
__Plan2Scene: Converting floorplans to 3D scenes__
[Madhawa Vidanapathirana](https://github.com/madhawav), [Qirui Wu](), [Yasutaka Furukawa](), [Angel X. Chang](https://github.com/angelxuanchang)
, [Manolis Savva](https://github.com/msavva)
[[Paper](https://arxiv.org/abs/2106.05375), [Project Page](https://3dlg-hcvc.github.io/plan2scene/), [Google Colab Demo](https://colab.research.google.com/drive/1lDkbfIV0drR1o9D0WYzoWeRskB91nXHq?usp=sharing)]
In the Plan2Scene task, we produce a textured 3D mesh of a residence from a floorplan and set of photos.
## Dependencies
1) We use a conda environment initialized as [described here](./docs/md/conda_env_setup.md).
2) Setup the `command line library` of [Embark Studios texture-synthesis](https://github.com/EmbarkStudios/texture-synthesis#command-line-binary) project.
1) You can download a pre-built binary [available here](https://github.com/EmbarkStudios/texture-synthesis/releases). Alternatively, you may build from the source.
2) Download the seam mask [available here](https://github.com/EmbarkStudios/texture-synthesis/blob/main/imgs/masks/1_tile.jpg).
3) Rename `./conf/plan2scene/seam_correct-example.json` to 'seam_correct.json' and update the paths to the texture synthesis command line library binary, and the seam mask.
Use 'code/src' as the source root when running python scripts.
```bash
export PYTHONPATH=./code/src
```
## Data
1) Rent3D++ dataset
1. Download and copy the [Rent3D++ dataset](https://forms.gle/mKAmnrzAm3LCK9ua6) to the `[PROJECT_ROOT]/data` directory. The data organization is [described here](docs/md/rent3dpp_data_organization.md).
2. [Optional] We have provided 3D scenes pre-populated with CAD models of objects.
If you wish to re-populate these scenes using the _Object Placement_ approach we use, [follow the instructions here](docs/md/place_cad_models.md).
3. To replicate our results, you should use the pre-extracted crops we provide.
These crops are provided with the Rent3D++ dataset and are copied to the `./data/processed/surface_crops` directory.
[Optional] If you wish to extract new crops instead of using these provided crops, following [these instructions](./docs/md/extract_crops.md).
4. Select ground truth reference crops and populate photo room assignment lists.
```bash
# Select ground truth reference crops.
python code/scripts/plan2scene/preprocessing/generate_reference_crops.py ./data/processed/gt_reference/train ./data/input/photo_assignments/train train
python code/scripts/plan2scene/preprocessing/generate_reference_crops.py ./data/processed/gt_reference/val ./data/input/photo_assignments/val val
python code/scripts/plan2scene/preprocessing/generate_reference_crops.py ./data/processed/gt_reference/test ./data/input/photo_assignments/test test
# We evaluate Plan2Scene by simulating photo un-observations.
# Generate photoroom.csv files considering different photo un-observation ratios.
python code/scripts/plan2scene/preprocessing/generate_unobserved_photo_assignments.py ./data/processed/photo_assignments/train ./data/input/photo_assignments/train ./data/input/unobserved_photos.json train
python code/scripts/plan2scene/preprocessing/generate_unobserved_photo_assignments.py ./data/processed/photo_assignments/val ./data/input/photo_assignments/val ./data/input/unobserved_photos.json val
python code/scripts/plan2scene/preprocessing/generate_unobserved_photo_assignments.py ./data/processed/photo_assignments/test ./data/input/photo_assignments/test ./data/input/unobserved_photos.json test
```
2) [Optional] Stationary Textures Dataset - We use one of the following datasets to train the texture synthesis model.
_Not required if you are using pre-trained models._
- __Version 1__: We use this dataset in our CExcerpt of 12,684 characters
Read on GitHub
15
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:bc022ded6643f21c, topic:computer-vision, topic:3d-reconstruction