Clone with HTTP

git clone https://www.modelscope.cn/Damo_XR_Lab/Self_Supervised_Depth_Completion.git

深度图补全介绍

任务

输入一张稀疏深度图，模型回返回补全后的稠密深度图。

模型描述

本模型基于Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera，

技术细节请见： [Paper] | [Project Page]

代码示例

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.outputs import OutputKeys

model_id = 'Damo_XR_Lab/Self_Supervised_Depth_Completion'
data_dir = MsDataset.load(
    'KITTI_Depth_Dataset',
    namespace='Damo_XR_Lab',
    split='test',
    download_mode=DownloadMode.FORCE_REDOWNLOAD
).config_kwargs['split_config']['test']
source_dir = os.path.join(data_dir, 'selected_data')

snapshot_path = snapshot_download(model_id)
logger.info('snapshot_path: %s', snapshot_path)
self_supervised_depth_completion = pipeline(
    task=Tasks.self_supervised_depth_completion,
    model=model_id)

result = self_supervised_depth_completion(
    dict(model_dir=snapshot_path, source_dir=source_dir))
cv2.imwrite('result.jpg', result[OutputKeys.OUTPUT])

相关论文以及引用信息

该模型借鉴了以下论文的思路或代码，感谢作者的贡献！

@article{ma2018self,
	title={Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera},
	author={Ma, Fangchang and Cavalheiro, Guilherme Venturelli and Karaman, Sertac},
	booktitle={ICRA},
	year={2019}
}
@article{Ma2017SparseToDense,
	title={Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image},
	author={Ma, Fangchang and Karaman, Sertac},
	booktitle={ICRA},
	year={2018}
}