naykun/horizon

Official implementation of HORIZON: High-Resolution Semantically Controlled Panorama Synthesis

HORIZON: High-Resolution Semantically Controlled Panorama Synthesis

Kun Yan  Lei Ji  Chenfei Wu  Jian Liang  Ming Zhou  Nan Duan  Shuai Ma 

AAAI 2024

Official implementation of HORIZON: High-Resolution Semantically Controlled Panorama Synthesis
A novel framework that generates high-quality, semantically-controlled 360-degree panoramas with minimal distortion

Updates

[Soon] Model weights release.

[01/2024] Code released.

[12/2023] Paper Accepted by AAAI 2024

[10/2022] Paper uploaded to arXiv.

Installation

Use Miniconda to setup environment for HORIZON. Setup the required environment by the following command:

conda env create -f env.yml
conda activate horizon

Download Pretrained Models

Please download our checkpoints from Azure Blob to run the following inference scripts. After download, make a ckpt folder follow the belown structure:

ckpt
├── CLIP
│   └── ViT-L-14.pt
├── dataset
│   └── pano #dataset folder
├── last.pth 
└── vqg
    └── VQGan16384F16.pth

Inference

bash script/inference.sh

When the inference finish, you'll get all the generated panorama under /ckpt/pano/horizon_mini/eval_visu/pred/

Citation

@misc{yan2022horizon,
      title={HORIZON: A High-Resolution Panorama Synthesis Framework}, 
      author={Kun Yan and Lei Ji and Chenfei Wu and Jian Liang and Ming Zhou and Nan Duan and Shuai Ma},
      year={2022},
      eprint={2210.04522},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

horizon's Issues

Weights download link

Could you please fix the azure blob link to download the checkpoints ?