This the official repo of Modality Guided Subnetwork for salient object detection (3DV 2021).
The pseudo depth is estimated by the MiDaS.
This code is based on the CVPR 2020 Adele
If you find this repo useful, please consider citing:
@inproceedings{wu2021modality,
title={Modality-guided subnetwork for salient object detection},
author={Wu, Zongwei and Allibert, Guillaume and Stolz, Christophe and Ma, Chao and Demonceaux, C{\'e}dric},
booktitle={2021 International Conference on 3D Vision (3DV)},
pages={515--524},
year={2021},
organization={IEEE}
}